Upload folder using huggingface_hub
#4
by
wwwangyulai
- opened
- .gitattributes +3 -0
- .ipynb_checkpoints/args-checkpoint.json +379 -0
- .ipynb_checkpoints/chat_template-checkpoint.jinja +331 -0
- .ipynb_checkpoints/config-checkpoint.json +72 -0
- .ipynb_checkpoints/generation_config-checkpoint.json +11 -0
- .ipynb_checkpoints/special_tokens_map-checkpoint.json +23 -0
- .ipynb_checkpoints/tokenizer-checkpoint.json +3 -0
- .ipynb_checkpoints/tokenizer_config-checkpoint.json +183 -0
- .msc +0 -0
- .mv +1 -0
- README.md +48 -3
- args.json +379 -0
- chat_template.jinja +331 -0
- config.json +72 -0
- generation_config.json +11 -0
- model-00001-of-00009.safetensors +3 -0
- model-00002-of-00009.safetensors +3 -0
- model-00003-of-00009.safetensors +3 -0
- model-00004-of-00009.safetensors +3 -0
- model-00005-of-00009.safetensors +3 -0
- model-00006-of-00009.safetensors +3 -0
- model-00007-of-00009.safetensors +3 -0
- model-00008-of-00009.safetensors +3 -0
- model-00009-of-00009.safetensors +3 -0
- model.safetensors.index.json +419 -0
- special_tokens_map.json +23 -0
- tokenizer.json +3 -0
- tokenizer_config.json +183 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
*.bin*.safetensors*.pt filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
.ipynb_checkpoints/tokenizer-checkpoint.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
.ipynb_checkpoints/args-checkpoint.json
ADDED
|
@@ -0,0 +1,379 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"output_dir": "./output",
|
| 3 |
+
"overwrite_output_dir": false,
|
| 4 |
+
"do_train": false,
|
| 5 |
+
"do_eval": false,
|
| 6 |
+
"do_predict": false,
|
| 7 |
+
"eval_strategy": "no",
|
| 8 |
+
"prediction_loss_only": false,
|
| 9 |
+
"per_device_train_batch_size": 1,
|
| 10 |
+
"per_device_eval_batch_size": 1,
|
| 11 |
+
"per_gpu_train_batch_size": null,
|
| 12 |
+
"per_gpu_eval_batch_size": null,
|
| 13 |
+
"gradient_accumulation_steps": 7,
|
| 14 |
+
"eval_accumulation_steps": null,
|
| 15 |
+
"eval_delay": 0,
|
| 16 |
+
"torch_empty_cache_steps": null,
|
| 17 |
+
"learning_rate": 5e-06,
|
| 18 |
+
"weight_decay": 0.1,
|
| 19 |
+
"adam_beta1": 0.9,
|
| 20 |
+
"adam_beta2": 0.95,
|
| 21 |
+
"adam_epsilon": 1e-08,
|
| 22 |
+
"max_grad_norm": 1.0,
|
| 23 |
+
"num_train_epochs": 6.0,
|
| 24 |
+
"max_steps": -1,
|
| 25 |
+
"lr_scheduler_type": "cosine",
|
| 26 |
+
"lr_scheduler_kwargs": null,
|
| 27 |
+
"warmup_ratio": 0.05,
|
| 28 |
+
"warmup_steps": 0,
|
| 29 |
+
"log_level": "passive",
|
| 30 |
+
"log_level_replica": "warning",
|
| 31 |
+
"log_on_each_node": true,
|
| 32 |
+
"logging_dir": "./output/logs",
|
| 33 |
+
"logging_strategy": "steps",
|
| 34 |
+
"logging_first_step": true,
|
| 35 |
+
"logging_steps": 5,
|
| 36 |
+
"logging_nan_inf_filter": true,
|
| 37 |
+
"save_strategy": "steps",
|
| 38 |
+
"save_steps": 1609.0,
|
| 39 |
+
"save_total_limit": 10,
|
| 40 |
+
"save_safetensors": true,
|
| 41 |
+
"save_on_each_node": false,
|
| 42 |
+
"save_only_model": false,
|
| 43 |
+
"restore_callback_states_from_checkpoint": false,
|
| 44 |
+
"no_cuda": false,
|
| 45 |
+
"use_cpu": false,
|
| 46 |
+
"use_mps_device": false,
|
| 47 |
+
"seed": 42,
|
| 48 |
+
"data_seed": 42,
|
| 49 |
+
"jit_mode_eval": false,
|
| 50 |
+
"use_ipex": false,
|
| 51 |
+
"bf16": true,
|
| 52 |
+
"fp16": false,
|
| 53 |
+
"fp16_opt_level": "O1",
|
| 54 |
+
"half_precision_backend": "auto",
|
| 55 |
+
"bf16_full_eval": false,
|
| 56 |
+
"fp16_full_eval": false,
|
| 57 |
+
"tf32": null,
|
| 58 |
+
"local_rank": 0,
|
| 59 |
+
"ddp_backend": null,
|
| 60 |
+
"tpu_num_cores": null,
|
| 61 |
+
"tpu_metrics_debug": false,
|
| 62 |
+
"debug": null,
|
| 63 |
+
"dataloader_drop_last": false,
|
| 64 |
+
"eval_steps": 1609.0,
|
| 65 |
+
"dataloader_num_workers": 192,
|
| 66 |
+
"dataloader_prefetch_factor": null,
|
| 67 |
+
"past_index": -1,
|
| 68 |
+
"run_name": "safety-model-training",
|
| 69 |
+
"disable_tqdm": null,
|
| 70 |
+
"remove_unused_columns": true,
|
| 71 |
+
"label_names": null,
|
| 72 |
+
"load_best_model_at_end": false,
|
| 73 |
+
"metric_for_best_model": "loss",
|
| 74 |
+
"greater_is_better": false,
|
| 75 |
+
"ignore_data_skip": false,
|
| 76 |
+
"fsdp": "",
|
| 77 |
+
"fsdp_min_num_params": 0,
|
| 78 |
+
"fsdp_config": null,
|
| 79 |
+
"fsdp_transformer_layer_cls_to_wrap": null,
|
| 80 |
+
"accelerator_config": {
|
| 81 |
+
"dispatch_batches": false
|
| 82 |
+
},
|
| 83 |
+
"deepspeed": {
|
| 84 |
+
"fp16": {
|
| 85 |
+
"enabled": "auto",
|
| 86 |
+
"loss_scale": 0,
|
| 87 |
+
"loss_scale_window": 1000,
|
| 88 |
+
"initial_scale_power": 16,
|
| 89 |
+
"hysteresis": 2,
|
| 90 |
+
"min_loss_scale": 1
|
| 91 |
+
},
|
| 92 |
+
"bf16": {
|
| 93 |
+
"enabled": "auto"
|
| 94 |
+
},
|
| 95 |
+
"zero_optimization": {
|
| 96 |
+
"stage": 3,
|
| 97 |
+
"offload_optimizer": {
|
| 98 |
+
"device": "none",
|
| 99 |
+
"pin_memory": true
|
| 100 |
+
},
|
| 101 |
+
"offload_param": {
|
| 102 |
+
"device": "none",
|
| 103 |
+
"pin_memory": true
|
| 104 |
+
},
|
| 105 |
+
"overlap_comm": false,
|
| 106 |
+
"contiguous_gradients": true,
|
| 107 |
+
"sub_group_size": 1000000000.0,
|
| 108 |
+
"reduce_bucket_size": "auto",
|
| 109 |
+
"zero_quantized_weights": false,
|
| 110 |
+
"zero_quantized_gradients": false,
|
| 111 |
+
"stage3_prefetch_bucket_size": "auto",
|
| 112 |
+
"stage3_param_persistence_threshold": "auto",
|
| 113 |
+
"stage3_max_live_parameters": 1000000000.0,
|
| 114 |
+
"stage3_max_reuse_distance": 1000000000.0,
|
| 115 |
+
"stage3_gather_16bit_weights_on_model_save": true
|
| 116 |
+
},
|
| 117 |
+
"gradient_accumulation_steps": "auto",
|
| 118 |
+
"gradient_clipping": "auto",
|
| 119 |
+
"steps_per_print": 2000,
|
| 120 |
+
"train_batch_size": "auto",
|
| 121 |
+
"train_micro_batch_size_per_gpu": "auto",
|
| 122 |
+
"wall_clock_breakdown": false
|
| 123 |
+
},
|
| 124 |
+
"label_smoothing_factor": 0.0,
|
| 125 |
+
"optim": "adamw_torch",
|
| 126 |
+
"optim_args": null,
|
| 127 |
+
"adafactor": false,
|
| 128 |
+
"group_by_length": false,
|
| 129 |
+
"length_column_name": "length",
|
| 130 |
+
"report_to": [
|
| 131 |
+
"tensorboard"
|
| 132 |
+
],
|
| 133 |
+
"ddp_find_unused_parameters": null,
|
| 134 |
+
"ddp_bucket_cap_mb": null,
|
| 135 |
+
"ddp_broadcast_buffers": null,
|
| 136 |
+
"dataloader_pin_memory": true,
|
| 137 |
+
"dataloader_persistent_workers": false,
|
| 138 |
+
"skip_memory_metrics": true,
|
| 139 |
+
"use_legacy_prediction_loop": false,
|
| 140 |
+
"push_to_hub": false,
|
| 141 |
+
"resume_from_checkpoint": null,
|
| 142 |
+
"hub_model_id": null,
|
| 143 |
+
"hub_strategy": "every_save",
|
| 144 |
+
"hub_token": null,
|
| 145 |
+
"hub_private_repo": null,
|
| 146 |
+
"hub_always_push": false,
|
| 147 |
+
"hub_revision": null,
|
| 148 |
+
"gradient_checkpointing": true,
|
| 149 |
+
"gradient_checkpointing_kwargs": null,
|
| 150 |
+
"include_inputs_for_metrics": false,
|
| 151 |
+
"include_for_metrics": [],
|
| 152 |
+
"eval_do_concat_batches": true,
|
| 153 |
+
"fp16_backend": "auto",
|
| 154 |
+
"push_to_hub_model_id": null,
|
| 155 |
+
"push_to_hub_organization": null,
|
| 156 |
+
"push_to_hub_token": null,
|
| 157 |
+
"mp_parameters": "",
|
| 158 |
+
"auto_find_batch_size": false,
|
| 159 |
+
"full_determinism": false,
|
| 160 |
+
"torchdynamo": null,
|
| 161 |
+
"ray_scope": "last",
|
| 162 |
+
"ddp_timeout": 18000000,
|
| 163 |
+
"torch_compile": false,
|
| 164 |
+
"torch_compile_backend": null,
|
| 165 |
+
"torch_compile_mode": null,
|
| 166 |
+
"include_tokens_per_second": false,
|
| 167 |
+
"include_num_input_tokens_seen": false,
|
| 168 |
+
"neftune_noise_alpha": null,
|
| 169 |
+
"optim_target_modules": null,
|
| 170 |
+
"batch_eval_metrics": false,
|
| 171 |
+
"eval_on_start": false,
|
| 172 |
+
"use_liger_kernel": false,
|
| 173 |
+
"liger_kernel_config": null,
|
| 174 |
+
"eval_use_gather_object": false,
|
| 175 |
+
"average_tokens_across_devices": true,
|
| 176 |
+
"sortish_sampler": false,
|
| 177 |
+
"predict_with_generate": false,
|
| 178 |
+
"generation_max_length": null,
|
| 179 |
+
"generation_num_beams": null,
|
| 180 |
+
"generation_config": null,
|
| 181 |
+
"vit_gradient_checkpointing": null,
|
| 182 |
+
"check_model": true,
|
| 183 |
+
"acc_strategy": "token",
|
| 184 |
+
"train_dataloader_shuffle": true,
|
| 185 |
+
"max_epochs": null,
|
| 186 |
+
"aligner_lr": null,
|
| 187 |
+
"vit_lr": null,
|
| 188 |
+
"optimizer": null,
|
| 189 |
+
"use_logits_to_keep": null,
|
| 190 |
+
"channels": null,
|
| 191 |
+
"ds3_gather_for_generation": true,
|
| 192 |
+
"metric_warmup_step": 0,
|
| 193 |
+
"fsdp_num": 1,
|
| 194 |
+
"acc_steps": 1,
|
| 195 |
+
"eval_use_evalscope": false,
|
| 196 |
+
"eval_dataset": [],
|
| 197 |
+
"eval_dataset_args": null,
|
| 198 |
+
"eval_limit": null,
|
| 199 |
+
"eval_generation_config": null,
|
| 200 |
+
"model": "JSL-joysafety-v1/gpt-oss-20b",
|
| 201 |
+
"model_type": null,
|
| 202 |
+
"model_revision": null,
|
| 203 |
+
"task_type": "causal_lm",
|
| 204 |
+
"torch_dtype": "bfloat16",
|
| 205 |
+
"attn_impl": "flash_attn",
|
| 206 |
+
"num_labels": null,
|
| 207 |
+
"problem_type": null,
|
| 208 |
+
"rope_scaling": {
|
| 209 |
+
"beta_fast": 32.0,
|
| 210 |
+
"beta_slow": 1.0,
|
| 211 |
+
"factor": 32.0,
|
| 212 |
+
"original_max_position_embeddings": 4096,
|
| 213 |
+
"rope_type": "yarn",
|
| 214 |
+
"truncate": false,
|
| 215 |
+
"type": "yarn"
|
| 216 |
+
},
|
| 217 |
+
"device_map": null,
|
| 218 |
+
"max_memory": {},
|
| 219 |
+
"local_repo_path": null,
|
| 220 |
+
"init_strategy": null,
|
| 221 |
+
"template": "default",
|
| 222 |
+
"system": null,
|
| 223 |
+
"max_length": 8192,
|
| 224 |
+
"truncation_strategy": "right",
|
| 225 |
+
"max_pixels": null,
|
| 226 |
+
"agent_template": null,
|
| 227 |
+
"norm_bbox": null,
|
| 228 |
+
"use_chat_template": true,
|
| 229 |
+
"padding_free": false,
|
| 230 |
+
"padding_side": "right",
|
| 231 |
+
"loss_scale": "default",
|
| 232 |
+
"sequence_parallel_size": 1,
|
| 233 |
+
"response_prefix": null,
|
| 234 |
+
"template_backend": "swift",
|
| 235 |
+
"dataset": [
|
| 236 |
+
"JSL-joysafety-v1/safety-dataset"
|
| 237 |
+
],
|
| 238 |
+
"val_dataset": [],
|
| 239 |
+
"split_dataset_ratio": 0.0,
|
| 240 |
+
"dataset_num_proc": 192,
|
| 241 |
+
"load_from_cache_file": true,
|
| 242 |
+
"dataset_shuffle": true,
|
| 243 |
+
"val_dataset_shuffle": false,
|
| 244 |
+
"streaming": false,
|
| 245 |
+
"interleave_prob": null,
|
| 246 |
+
"stopping_strategy": "first_exhausted",
|
| 247 |
+
"shuffle_buffer_size": 1000,
|
| 248 |
+
"download_mode": "reuse_dataset_if_exists",
|
| 249 |
+
"columns": {},
|
| 250 |
+
"strict": false,
|
| 251 |
+
"model_name": null,
|
| 252 |
+
"model_author": null,
|
| 253 |
+
"custom_dataset_info": [],
|
| 254 |
+
"quant_method": null,
|
| 255 |
+
"quant_bits": null,
|
| 256 |
+
"hqq_axis": null,
|
| 257 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
| 258 |
+
"bnb_4bit_quant_type": "nf4",
|
| 259 |
+
"bnb_4bit_use_double_quant": true,
|
| 260 |
+
"bnb_4bit_quant_storage": null,
|
| 261 |
+
"max_new_tokens": 64,
|
| 262 |
+
"temperature": 0.0,
|
| 263 |
+
"top_k": null,
|
| 264 |
+
"top_p": null,
|
| 265 |
+
"repetition_penalty": null,
|
| 266 |
+
"num_beams": 1,
|
| 267 |
+
"stream": false,
|
| 268 |
+
"stop_words": [],
|
| 269 |
+
"logprobs": false,
|
| 270 |
+
"top_logprobs": null,
|
| 271 |
+
"ckpt_dir": null,
|
| 272 |
+
"lora_modules": [],
|
| 273 |
+
"tuner_backend": "peft",
|
| 274 |
+
"train_type": "full",
|
| 275 |
+
"adapters": [],
|
| 276 |
+
"external_plugins": [],
|
| 277 |
+
"model_kwargs": {},
|
| 278 |
+
"load_args": false,
|
| 279 |
+
"load_data_args": false,
|
| 280 |
+
"packing": false,
|
| 281 |
+
"packing_cache": null,
|
| 282 |
+
"custom_register_path": [],
|
| 283 |
+
"use_hf": false,
|
| 284 |
+
"ignore_args_error": false,
|
| 285 |
+
"use_swift_lora": false,
|
| 286 |
+
"freeze_parameters": [],
|
| 287 |
+
"freeze_parameters_regex": null,
|
| 288 |
+
"freeze_parameters_ratio": 0.0,
|
| 289 |
+
"trainable_parameters": [],
|
| 290 |
+
"trainable_parameters_regex": null,
|
| 291 |
+
"freeze_llm": false,
|
| 292 |
+
"freeze_vit": true,
|
| 293 |
+
"freeze_aligner": true,
|
| 294 |
+
"target_modules": [
|
| 295 |
+
"all-linear"
|
| 296 |
+
],
|
| 297 |
+
"target_regex": null,
|
| 298 |
+
"modules_to_save": [],
|
| 299 |
+
"lora_rank": 8,
|
| 300 |
+
"lora_alpha": 32,
|
| 301 |
+
"lora_dropout": 0.05,
|
| 302 |
+
"lora_bias": "none",
|
| 303 |
+
"lora_dtype": null,
|
| 304 |
+
"lorap_lr_ratio": null,
|
| 305 |
+
"use_rslora": false,
|
| 306 |
+
"use_dora": false,
|
| 307 |
+
"lora_ga_batch_size": 2,
|
| 308 |
+
"lora_ga_iters": 2,
|
| 309 |
+
"lora_ga_max_length": 1024,
|
| 310 |
+
"lora_ga_direction": "ArB2r",
|
| 311 |
+
"lora_ga_scale": "stable",
|
| 312 |
+
"lora_ga_stable_gamma": 16,
|
| 313 |
+
"init_weights": true,
|
| 314 |
+
"fourier_n_frequency": 2000,
|
| 315 |
+
"fourier_scaling": 300.0,
|
| 316 |
+
"boft_block_size": 4,
|
| 317 |
+
"boft_block_num": 0,
|
| 318 |
+
"boft_n_butterfly_factor": 1,
|
| 319 |
+
"boft_dropout": 0.0,
|
| 320 |
+
"vera_rank": 256,
|
| 321 |
+
"vera_projection_prng_key": 0,
|
| 322 |
+
"vera_dropout": 0.0,
|
| 323 |
+
"vera_d_initial": 0.1,
|
| 324 |
+
"adapter_act": "gelu",
|
| 325 |
+
"adapter_length": 128,
|
| 326 |
+
"use_galore": false,
|
| 327 |
+
"galore_target_modules": null,
|
| 328 |
+
"galore_rank": 128,
|
| 329 |
+
"galore_update_proj_gap": 50,
|
| 330 |
+
"galore_scale": 1.0,
|
| 331 |
+
"galore_proj_type": "std",
|
| 332 |
+
"galore_optim_per_parameter": false,
|
| 333 |
+
"galore_with_embedding": false,
|
| 334 |
+
"galore_quantization": false,
|
| 335 |
+
"galore_proj_quant": false,
|
| 336 |
+
"galore_proj_bits": 4,
|
| 337 |
+
"galore_proj_group_size": 256,
|
| 338 |
+
"galore_cos_threshold": 0.4,
|
| 339 |
+
"galore_gamma_proj": 2,
|
| 340 |
+
"galore_queue_size": 5,
|
| 341 |
+
"adalora_target_r": 8,
|
| 342 |
+
"adalora_init_r": 12,
|
| 343 |
+
"adalora_tinit": 0,
|
| 344 |
+
"adalora_tfinal": 0,
|
| 345 |
+
"adalora_deltaT": 1,
|
| 346 |
+
"adalora_beta1": 0.85,
|
| 347 |
+
"adalora_beta2": 0.85,
|
| 348 |
+
"adalora_orth_reg_weight": 0.5,
|
| 349 |
+
"llamapro_num_new_blocks": 4,
|
| 350 |
+
"llamapro_num_groups": null,
|
| 351 |
+
"lisa_activated_layers": 0,
|
| 352 |
+
"lisa_step_interval": 20,
|
| 353 |
+
"reft_layer_key": null,
|
| 354 |
+
"reft_layers": null,
|
| 355 |
+
"reft_rank": 4,
|
| 356 |
+
"reft_intervention_type": "LoreftIntervention",
|
| 357 |
+
"reft_args": null,
|
| 358 |
+
"swanlab_token": null,
|
| 359 |
+
"swanlab_project": null,
|
| 360 |
+
"swanlab_workspace": null,
|
| 361 |
+
"swanlab_exp_name": null,
|
| 362 |
+
"swanlab_lark_webhook_url": null,
|
| 363 |
+
"swanlab_lark_secret": null,
|
| 364 |
+
"swanlab_mode": "cloud",
|
| 365 |
+
"add_version": true,
|
| 366 |
+
"resume_only_model": false,
|
| 367 |
+
"create_checkpoint_symlink": false,
|
| 368 |
+
"lazy_tokenize": false,
|
| 369 |
+
"loss_type": null,
|
| 370 |
+
"metric": null,
|
| 371 |
+
"zero_hpz_partition_size": null,
|
| 372 |
+
"rank": 0,
|
| 373 |
+
"global_world_size": 40,
|
| 374 |
+
"local_world_size": 8,
|
| 375 |
+
"model_suffix": "gpt-oss-20b",
|
| 376 |
+
"model_meta": "ModelMeta(model_type=None, model_groups=[], template='dummy', get_function=<function get_model_tokenizer_from_local at 0x7f67a0a7b130>, model_arch=None, architectures=[], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, task_type=None, ignore_patterns=None, requires=[], tags=[])",
|
| 377 |
+
"model_dir": "/mnt/workspace/public_model/gpt-oss-20b",
|
| 378 |
+
"evaluation_strategy": "steps"
|
| 379 |
+
}
|
.ipynb_checkpoints/chat_template-checkpoint.jinja
ADDED
|
@@ -0,0 +1,331 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{#-
|
| 2 |
+
In addition to the normal inputs of `messages` and `tools`, this template also accepts the
|
| 3 |
+
following kwargs:
|
| 4 |
+
- "builtin_tools": A list, can contain "browser" and/or "python".
|
| 5 |
+
- "model_identity": A string that optionally describes the model identity.
|
| 6 |
+
- "reasoning_effort": A string that describes the reasoning effort, defaults to "medium".
|
| 7 |
+
#}
|
| 8 |
+
|
| 9 |
+
{#- Tool Definition Rendering ============================================== #}
|
| 10 |
+
{%- macro render_typescript_type(param_spec, required_params, is_nullable=false) -%}
|
| 11 |
+
{%- if param_spec.type == "array" -%}
|
| 12 |
+
{%- if param_spec['items'] -%}
|
| 13 |
+
{%- if param_spec['items']['type'] == "string" -%}
|
| 14 |
+
{{- "string[]" }}
|
| 15 |
+
{%- elif param_spec['items']['type'] == "number" -%}
|
| 16 |
+
{{- "number[]" }}
|
| 17 |
+
{%- elif param_spec['items']['type'] == "integer" -%}
|
| 18 |
+
{{- "number[]" }}
|
| 19 |
+
{%- elif param_spec['items']['type'] == "boolean" -%}
|
| 20 |
+
{{- "boolean[]" }}
|
| 21 |
+
{%- else -%}
|
| 22 |
+
{%- set inner_type = render_typescript_type(param_spec['items'], required_params) -%}
|
| 23 |
+
{%- if inner_type == "object | object" or inner_type|length > 50 -%}
|
| 24 |
+
{{- "any[]" }}
|
| 25 |
+
{%- else -%}
|
| 26 |
+
{{- inner_type + "[]" }}
|
| 27 |
+
{%- endif -%}
|
| 28 |
+
{%- endif -%}
|
| 29 |
+
{%- if param_spec.nullable -%}
|
| 30 |
+
{{- " | null" }}
|
| 31 |
+
{%- endif -%}
|
| 32 |
+
{%- else -%}
|
| 33 |
+
{{- "any[]" }}
|
| 34 |
+
{%- if param_spec.nullable -%}
|
| 35 |
+
{{- " | null" }}
|
| 36 |
+
{%- endif -%}
|
| 37 |
+
{%- endif -%}
|
| 38 |
+
{%- elif param_spec.type is defined and param_spec.type is iterable and param_spec.type is not string and param_spec.type is not mapping and param_spec.type[0] is defined -%}
|
| 39 |
+
{#- Handle array of types like ["object", "object"] from Union[dict, list] #}
|
| 40 |
+
{%- if param_spec.type | length > 1 -%}
|
| 41 |
+
{{- param_spec.type | join(" | ") }}
|
| 42 |
+
{%- else -%}
|
| 43 |
+
{{- param_spec.type[0] }}
|
| 44 |
+
{%- endif -%}
|
| 45 |
+
{%- elif param_spec.oneOf -%}
|
| 46 |
+
{#- Handle oneOf schemas - check for complex unions and fallback to any #}
|
| 47 |
+
{%- set has_object_variants = false -%}
|
| 48 |
+
{%- for variant in param_spec.oneOf -%}
|
| 49 |
+
{%- if variant.type == "object" -%}
|
| 50 |
+
{%- set has_object_variants = true -%}
|
| 51 |
+
{%- endif -%}
|
| 52 |
+
{%- endfor -%}
|
| 53 |
+
{%- if has_object_variants and param_spec.oneOf|length > 1 -%}
|
| 54 |
+
{{- "any" }}
|
| 55 |
+
{%- else -%}
|
| 56 |
+
{%- for variant in param_spec.oneOf -%}
|
| 57 |
+
{{- render_typescript_type(variant, required_params) -}}
|
| 58 |
+
{%- if variant.description %}
|
| 59 |
+
{{- "// " + variant.description }}
|
| 60 |
+
{%- endif -%}
|
| 61 |
+
{%- if variant.default is defined %}
|
| 62 |
+
{{ "// default: " + variant.default|tojson }}
|
| 63 |
+
{%- endif -%}
|
| 64 |
+
{%- if not loop.last %}
|
| 65 |
+
{{- " | " }}
|
| 66 |
+
{% endif -%}
|
| 67 |
+
{%- endfor -%}
|
| 68 |
+
{%- endif -%}
|
| 69 |
+
{%- elif param_spec.type == "string" -%}
|
| 70 |
+
{%- if param_spec.enum -%}
|
| 71 |
+
{{- '"' + param_spec.enum|join('" | "') + '"' -}}
|
| 72 |
+
{%- else -%}
|
| 73 |
+
{{- "string" }}
|
| 74 |
+
{%- if param_spec.nullable %}
|
| 75 |
+
{{- " | null" }}
|
| 76 |
+
{%- endif -%}
|
| 77 |
+
{%- endif -%}
|
| 78 |
+
{%- elif param_spec.type == "number" -%}
|
| 79 |
+
{{- "number" }}
|
| 80 |
+
{%- elif param_spec.type == "integer" -%}
|
| 81 |
+
{{- "number" }}
|
| 82 |
+
{%- elif param_spec.type == "boolean" -%}
|
| 83 |
+
{{- "boolean" }}
|
| 84 |
+
|
| 85 |
+
{%- elif param_spec.type == "object" -%}
|
| 86 |
+
{%- if param_spec.properties -%}
|
| 87 |
+
{{- "{\n" }}
|
| 88 |
+
{%- for prop_name, prop_spec in param_spec.properties.items() -%}
|
| 89 |
+
{{- prop_name -}}
|
| 90 |
+
{%- if prop_name not in (param_spec.required or []) -%}
|
| 91 |
+
{{- "?" }}
|
| 92 |
+
{%- endif -%}
|
| 93 |
+
{{- ": " }}
|
| 94 |
+
{{ render_typescript_type(prop_spec, param_spec.required or []) }}
|
| 95 |
+
{%- if not loop.last -%}
|
| 96 |
+
{{-", " }}
|
| 97 |
+
{%- endif -%}
|
| 98 |
+
{%- endfor -%}
|
| 99 |
+
{{- "}" }}
|
| 100 |
+
{%- else -%}
|
| 101 |
+
{{- "object" }}
|
| 102 |
+
{%- endif -%}
|
| 103 |
+
{%- else -%}
|
| 104 |
+
{{- "any" }}
|
| 105 |
+
{%- endif -%}
|
| 106 |
+
{%- endmacro -%}
|
| 107 |
+
|
| 108 |
+
{%- macro render_tool_namespace(namespace_name, tools) -%}
|
| 109 |
+
{{- "## " + namespace_name + "\n\n" }}
|
| 110 |
+
{{- "namespace " + namespace_name + " {\n\n" }}
|
| 111 |
+
{%- for tool in tools %}
|
| 112 |
+
{%- set tool = tool.function %}
|
| 113 |
+
{{- "// " + tool.description + "\n" }}
|
| 114 |
+
{{- "type "+ tool.name + " = " }}
|
| 115 |
+
{%- if tool.parameters and tool.parameters.properties %}
|
| 116 |
+
{{- "(_: {\n" }}
|
| 117 |
+
{%- for param_name, param_spec in tool.parameters.properties.items() %}
|
| 118 |
+
{%- if param_spec.description %}
|
| 119 |
+
{{- "// " + param_spec.description + "\n" }}
|
| 120 |
+
{%- endif %}
|
| 121 |
+
{{- param_name }}
|
| 122 |
+
{%- if param_name not in (tool.parameters.required or []) -%}
|
| 123 |
+
{{- "?" }}
|
| 124 |
+
{%- endif -%}
|
| 125 |
+
{{- ": " }}
|
| 126 |
+
{{- render_typescript_type(param_spec, tool.parameters.required or []) }}
|
| 127 |
+
{%- if param_spec.default is defined -%}
|
| 128 |
+
{%- if param_spec.enum %}
|
| 129 |
+
{{- ", // default: " + param_spec.default }}
|
| 130 |
+
{%- elif param_spec.oneOf %}
|
| 131 |
+
{{- "// default: " + param_spec.default }}
|
| 132 |
+
{%- else %}
|
| 133 |
+
{{- ", // default: " + param_spec.default|tojson }}
|
| 134 |
+
{%- endif -%}
|
| 135 |
+
{%- endif -%}
|
| 136 |
+
{%- if not loop.last %}
|
| 137 |
+
{{- ",\n" }}
|
| 138 |
+
{%- else %}
|
| 139 |
+
{{- ",\n" }}
|
| 140 |
+
{%- endif -%}
|
| 141 |
+
{%- endfor %}
|
| 142 |
+
{{- "}) => any;\n\n" }}
|
| 143 |
+
{%- else -%}
|
| 144 |
+
{{- "() => any;\n\n" }}
|
| 145 |
+
{%- endif -%}
|
| 146 |
+
{%- endfor %}
|
| 147 |
+
{{- "} // namespace " + namespace_name }}
|
| 148 |
+
{%- endmacro -%}
|
| 149 |
+
|
| 150 |
+
{%- macro render_builtin_tools(browser_tool, python_tool) -%}
|
| 151 |
+
{%- if browser_tool %}
|
| 152 |
+
{{- "## browser\n\n" }}
|
| 153 |
+
{{- "// Tool for browsing.\n" }}
|
| 154 |
+
{{- "// The `cursor` appears in brackets before each browsing display: `[{cursor}]`.\n" }}
|
| 155 |
+
{{- "// Cite information from the tool using the following format:\n" }}
|
| 156 |
+
{{- "// `【{cursor}†L{line_start}(-L{line_end})?】`, for example: `【6†L9-L11】` or `【8†L3】`.\n" }}
|
| 157 |
+
{{- "// Do not quote more than 10 words directly from the tool output.\n" }}
|
| 158 |
+
{{- "// sources=web (default: web)\n" }}
|
| 159 |
+
{{- "namespace browser {\n\n" }}
|
| 160 |
+
{{- "// Searches for information related to `query` and displays `topn` results.\n" }}
|
| 161 |
+
{{- "type search = (_: {\n" }}
|
| 162 |
+
{{- "query: string,\n" }}
|
| 163 |
+
{{- "topn?: number, // default: 10\n" }}
|
| 164 |
+
{{- "source?: string,\n" }}
|
| 165 |
+
{{- "}) => any;\n\n" }}
|
| 166 |
+
{{- "// Opens the link `id` from the page indicated by `cursor` starting at line number `loc`, showing `num_lines` lines.\n" }}
|
| 167 |
+
{{- "// Valid link ids are displayed with the formatting: `【{id}†.*】`.\n" }}
|
| 168 |
+
{{- "// If `cursor` is not provided, the most recent page is implied.\n" }}
|
| 169 |
+
{{- "// If `id` is a string, it is treated as a fully qualified URL associated with `source`.\n" }}
|
| 170 |
+
{{- "// If `loc` is not provided, the viewport will be positioned at the beginning of the document or centered on the most relevant passage, if available.\n" }}
|
| 171 |
+
{{- "// Use this function without `id` to scroll to a new location of an opened page.\n" }}
|
| 172 |
+
{{- "type open = (_: {\n" }}
|
| 173 |
+
{{- "id?: number | string, // default: -1\n" }}
|
| 174 |
+
{{- "cursor?: number, // default: -1\n" }}
|
| 175 |
+
{{- "loc?: number, // default: -1\n" }}
|
| 176 |
+
{{- "num_lines?: number, // default: -1\n" }}
|
| 177 |
+
{{- "view_source?: boolean, // default: false\n" }}
|
| 178 |
+
{{- "source?: string,\n" }}
|
| 179 |
+
{{- "}) => any;\n\n" }}
|
| 180 |
+
{{- "// Finds exact matches of `pattern` in the current page, or the page given by `cursor`.\n" }}
|
| 181 |
+
{{- "type find = (_: {\n" }}
|
| 182 |
+
{{- "pattern: string,\n" }}
|
| 183 |
+
{{- "cursor?: number, // default: -1\n" }}
|
| 184 |
+
{{- "}) => any;\n\n" }}
|
| 185 |
+
{{- "} // namespace browser\n\n" }}
|
| 186 |
+
{%- endif -%}
|
| 187 |
+
|
| 188 |
+
{%- if python_tool %}
|
| 189 |
+
{{- "## python\n\n" }}
|
| 190 |
+
{{- "Use this tool to execute Python code in your chain of thought. The code will not be shown to the user. This tool should be used for internal reasoning, but not for code that is intended to be visible to the user (e.g. when creating plots, tables, or files).\n\n" }}
|
| 191 |
+
{{- "When you send a message containing Python code to python, it will be executed in a stateful Jupyter notebook environment. python will respond with the output of the execution or time out after 120.0 seconds. The drive at '/mnt/data' can be used to save and persist user files. Internet access for this session is UNKNOWN. Depends on the cluster.\n\n" }}
|
| 192 |
+
{%- endif -%}
|
| 193 |
+
{%- endmacro -%}
|
| 194 |
+
|
| 195 |
+
{#- System Message Construction ============================================ #}
|
| 196 |
+
{%- macro build_system_message() -%}
|
| 197 |
+
{%- if model_identity is not defined %}
|
| 198 |
+
{%- set model_identity = "\n\n你是一名「大模型内容安全审核专家」，请根据下面的风险审核checklist完成风险审核;\n\n#【任务描述】:\n\n 在 AI 对话场景中，完成用户输入与大模型回答安全审核，识别其中是否存在风险内容及诱导性风险。\n \n# 【注意事项】:\n 1. 按照《生成式人工智能服务管理暂行办法》进行风险审核； \n 2. 输出仅返回 JSON，不要附加任何解释性文字。 \n\n# 【风险审核-checklist】:\n\n 判断用户输入是否存在以下风险类型：涉政、暴恐、涉黄、涉赌、涉毒、辱骂、违禁、歧视、其他侵犯他人权益、其他商业违法违规等相关风险；无任何风险则归类为“正常文本”\n\n**输出格式**（JSON，禁止省略任何字段）：\n\n```json\n{\n \"reason\":\"cot分析过程\",\n \"risk_level\": 无风险|低风险|中风险|高风险, \n \"hit_categories\": [\"****\",\"****:],\n \"hit_detaile_categories\":[\"****\",\"****\"]\n \"risk_tags\"[] \n \"risk_roler\":\"user|\"ai\"|\"user&ai\",\n \"hit_keywords\": [\"xxx\"], \n \"suggestion\": \"pass\"|\"mask\"|\"block\"|\"review\"|\"proxy_answer\"\n}\n```\n**输出格式声明**\n reason:存放推理过程；\n risk_level:存放风险级别，分成四档:无风险|低风险|中风险|高风险；\n hit_categories:存放识别到的一级风险类别标签；\n hit_detaile_categories:存放识别到的二级风险类别标签；\n risk_tags:详细风险类型；\n risk_roler:存放对话中触发风险角色，user代表用户输入有风险，user&ai代表用户输入大模型回复都有风险，ai代表大模型回复有风险；\n hit_keywords:触发风险的原文片段；\n suggestion:建议处置策略；\n" %}
|
| 199 |
+
{%- endif %}
|
| 200 |
+
{{- model_identity + "\n" }}
|
| 201 |
+
{{- "Knowledge cutoff: 2024-06\n" }}
|
| 202 |
+
{{- "Current date: " + strftime_now("%Y-%m-%d") + "\n\n" }}
|
| 203 |
+
{%- if reasoning_effort is not defined %}
|
| 204 |
+
{%- set reasoning_effort = "medium" %}
|
| 205 |
+
{%- endif %}
|
| 206 |
+
{{- "Reasoning: " + reasoning_effort + "\n\n" }}
|
| 207 |
+
{%- if builtin_tools %}
|
| 208 |
+
{{- "# Tools\n\n" }}
|
| 209 |
+
{%- set available_builtin_tools = namespace(browser=false, python=false) %}
|
| 210 |
+
{%- for tool in builtin_tools %}
|
| 211 |
+
{%- if tool == "browser" %}
|
| 212 |
+
{%- set available_builtin_tools.browser = true %}
|
| 213 |
+
{%- elif tool == "python" %}
|
| 214 |
+
{%- set available_builtin_tools.python = true %}
|
| 215 |
+
{%- endif %}
|
| 216 |
+
{%- endfor %}
|
| 217 |
+
{{- render_builtin_tools(available_builtin_tools.browser, available_builtin_tools.python) }}
|
| 218 |
+
{%- endif -%}
|
| 219 |
+
{{- "# Valid channels: analysis, commentary, final. Channel must be included for every message." }}
|
| 220 |
+
{%- if tools -%}
|
| 221 |
+
{{- "\nCalls to these tools must go to the commentary channel: 'functions'." }}
|
| 222 |
+
{%- endif -%}
|
| 223 |
+
{%- endmacro -%}
|
| 224 |
+
|
| 225 |
+
{#- Main Template Logic ================================================= #}
|
| 226 |
+
{#- Set defaults #}
|
| 227 |
+
|
| 228 |
+
{#- Render system message #}
|
| 229 |
+
{{- "<|start|>system<|message|>" }}
|
| 230 |
+
{{- build_system_message() }}
|
| 231 |
+
{{- "<|end|>" }}
|
| 232 |
+
|
| 233 |
+
{#- Extract developer message #}
|
| 234 |
+
{%- if messages[0].role == "developer" or messages[0].role == "system" %}
|
| 235 |
+
{%- set developer_message = messages[0].content %}
|
| 236 |
+
{%- set loop_messages = messages[1:] %}
|
| 237 |
+
{%- else %}
|
| 238 |
+
{%- set developer_message = "" %}
|
| 239 |
+
{%- set loop_messages = messages %}
|
| 240 |
+
{%- endif %}
|
| 241 |
+
|
| 242 |
+
{#- Render developer message #}
|
| 243 |
+
{%- if developer_message or tools %}
|
| 244 |
+
{{- "<|start|>developer<|message|>" }}
|
| 245 |
+
{%- if developer_message %}
|
| 246 |
+
{{- "# Instructions\n\n" }}
|
| 247 |
+
{{- developer_message }}
|
| 248 |
+
{{- "\n\n" }}
|
| 249 |
+
{%- endif %}
|
| 250 |
+
{%- if tools -%}
|
| 251 |
+
{{- "# Tools\n\n" }}
|
| 252 |
+
{{- render_tool_namespace("functions", tools) }}
|
| 253 |
+
{%- endif -%}
|
| 254 |
+
{{- "<|end|>" }}
|
| 255 |
+
{%- endif %}
|
| 256 |
+
|
| 257 |
+
{#- Render messages #}
|
| 258 |
+
{%- set last_tool_call = namespace(name=none) %}
|
| 259 |
+
{%- for message in loop_messages -%}
|
| 260 |
+
{#- At this point only assistant/user/tool messages should remain #}
|
| 261 |
+
{%- if message.role == 'assistant' -%}
|
| 262 |
+
{#- Checks to ensure the messages are being passed in the format we expect #}
|
| 263 |
+
{%- if "content" in message %}
|
| 264 |
+
{%- if "<|channel|>analysis<|message|>" in message.content or "<|channel|>final<|message|>" in message.content %}
|
| 265 |
+
{{- raise_exception("You have passed a message containing <|channel|> tags in the content field. Instead of doing this, you should pass analysis messages (the string between '<|message|>' and '<|end|>') in the 'thinking' field, and final messages (the string between '<|message|>' and '<|end|>') in the 'content' field.") }}
|
| 266 |
+
{%- endif %}
|
| 267 |
+
{%- endif %}
|
| 268 |
+
{%- if "thinking" in message %}
|
| 269 |
+
{%- if "<|channel|>analysis<|message|>" in message.thinking or "<|channel|>final<|message|>" in message.thinking %}
|
| 270 |
+
{{- raise_exception("You have passed a message containing <|channel|> tags in the thinking field. Instead of doing this, you should pass analysis messages (the string between '<|message|>' and '<|end|>') in the 'thinking' field, and final messages (the string between '<|message|>' and '<|end|>') in the 'content' field.") }}
|
| 271 |
+
{%- endif %}
|
| 272 |
+
{%- endif %}
|
| 273 |
+
{%- if "tool_calls" in message %}
|
| 274 |
+
{#- We need very careful handling here - we want to drop the tool call analysis message if the model #}
|
| 275 |
+
{#- has output a later <|final|> message, but otherwise we want to retain it. This is the only case #}
|
| 276 |
+
{#- when we render CoT/analysis messages in inference. #}
|
| 277 |
+
{%- set future_final_message = namespace(found=false) %}
|
| 278 |
+
{%- for future_message in loop_messages[loop.index:] %}
|
| 279 |
+
{%- if future_message.role == 'assistant' and "tool_calls" not in future_message %}
|
| 280 |
+
{%- set future_final_message.found = true %}
|
| 281 |
+
{%- endif %}
|
| 282 |
+
{%- endfor %}
|
| 283 |
+
{#- We assume max 1 tool call per message, and so we infer the tool call name #}
|
| 284 |
+
{#- in "tool" messages from the most recent assistant tool call name #}
|
| 285 |
+
{%- set tool_call = message.tool_calls[0] %}
|
| 286 |
+
{%- if tool_call.function %}
|
| 287 |
+
{%- set tool_call = tool_call.function %}
|
| 288 |
+
{%- endif %}
|
| 289 |
+
{%- if message.content and message.thinking %}
|
| 290 |
+
{{- raise_exception("Cannot pass both content and thinking in an assistant message with tool calls! Put the analysis message in one or the other, but not both.") }}
|
| 291 |
+
{%- elif message.content and not future_final_message.found %}
|
| 292 |
+
{{- "<|start|>assistant<|channel|>analysis<|message|>" + message.content + "<|end|>" }}
|
| 293 |
+
{%- elif message.thinking and not future_final_message.found %}
|
| 294 |
+
{{- "<|start|>assistant<|channel|>analysis<|message|>" + message.thinking + "<|end|>" }}
|
| 295 |
+
{%- endif %}
|
| 296 |
+
{{- "<|start|>assistant to=" }}
|
| 297 |
+
{{- "functions." + tool_call.name + "<|channel|>commentary " }}
|
| 298 |
+
{{- (tool_call.content_type if tool_call.content_type is defined else "json") + "<|message|>" }}
|
| 299 |
+
{{- tool_call.arguments|tojson }}
|
| 300 |
+
{{- "<|call|>" }}
|
| 301 |
+
{%- set last_tool_call.name = tool_call.name %}
|
| 302 |
+
{%- elif loop.last and not add_generation_prompt %}
|
| 303 |
+
{#- Only render the CoT if the final turn is an assistant turn and add_generation_prompt is false #}
|
| 304 |
+
{#- This is a situation that should only occur in training, never in inference. #}
|
| 305 |
+
{%- if "thinking" in message %}
|
| 306 |
+
{{- "<|start|>assistant<|channel|>analysis<|message|>" + message.thinking + "<|end|>" }}
|
| 307 |
+
{%- endif %}
|
| 308 |
+
{#- <|return|> indicates the end of generation, but <|end|> does not #}
|
| 309 |
+
{#- <|return|> should never be an input to the model, but we include it as the final token #}
|
| 310 |
+
{#- when training, so the model learns to emit it. #}
|
| 311 |
+
{{- "<|start|>assistant<|channel|>final<|message|>" + message.content + "<|return|>" }}
|
| 312 |
+
{%- else %}
|
| 313 |
+
{#- CoT is dropped during all previous turns, so we never render it for inference #}
|
| 314 |
+
{{- "<|start|>assistant<|channel|>final<|message|>" + message.content + "<|end|>" }}
|
| 315 |
+
{%- set last_tool_call.name = none %}
|
| 316 |
+
{%- endif %}
|
| 317 |
+
{%- elif message.role == 'tool' -%}
|
| 318 |
+
{%- if last_tool_call.name is none %}
|
| 319 |
+
{{- raise_exception("Message has tool role, but there was no previous assistant message with a tool call!") }}
|
| 320 |
+
{%- endif %}
|
| 321 |
+
{{- "<|start|>functions." + last_tool_call.name }}
|
| 322 |
+
{{- " to=assistant<|channel|>commentary<|message|>" + message.content|tojson + "<|end|>" }}
|
| 323 |
+
{%- elif message.role == 'user' -%}
|
| 324 |
+
{{- "<|start|>user<|message|>" + message.content + "<|end|>" }}
|
| 325 |
+
{%- endif -%}
|
| 326 |
+
{%- endfor -%}
|
| 327 |
+
|
| 328 |
+
{#- Generation prompt #}
|
| 329 |
+
{%- if add_generation_prompt -%}
|
| 330 |
+
<|start|>assistant
|
| 331 |
+
{%- endif -%}
|
.ipynb_checkpoints/config-checkpoint.json
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"GptOssForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": true,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"eos_token_id": 200002,
|
| 8 |
+
"experts_per_token": 4,
|
| 9 |
+
"head_dim": 64,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2880,
|
| 12 |
+
"initial_context_length": 4096,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 2880,
|
| 15 |
+
"keys_to_ignore_at_inference": [
|
| 16 |
+
"past_key_values"
|
| 17 |
+
],
|
| 18 |
+
"layer_types": [
|
| 19 |
+
"sliding_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"sliding_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"sliding_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"sliding_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"sliding_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"sliding_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"sliding_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"sliding_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"sliding_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"sliding_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"sliding_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"sliding_attention",
|
| 42 |
+
"full_attention"
|
| 43 |
+
],
|
| 44 |
+
"max_position_embeddings": 131072,
|
| 45 |
+
"model_type": "gpt_oss",
|
| 46 |
+
"num_attention_heads": 64,
|
| 47 |
+
"num_experts_per_tok": 4,
|
| 48 |
+
"num_hidden_layers": 24,
|
| 49 |
+
"num_key_value_heads": 8,
|
| 50 |
+
"num_local_experts": 32,
|
| 51 |
+
"output_router_logits": false,
|
| 52 |
+
"pad_token_id": 199999,
|
| 53 |
+
"rms_norm_eps": 1e-05,
|
| 54 |
+
"rope_scaling": {
|
| 55 |
+
"beta_fast": 32.0,
|
| 56 |
+
"beta_slow": 1.0,
|
| 57 |
+
"factor": 32.0,
|
| 58 |
+
"original_max_position_embeddings": 4096,
|
| 59 |
+
"rope_type": "yarn",
|
| 60 |
+
"truncate": false,
|
| 61 |
+
"type": "yarn"
|
| 62 |
+
},
|
| 63 |
+
"rope_theta": 150000,
|
| 64 |
+
"router_aux_loss_coef": 0.9,
|
| 65 |
+
"sliding_window": 128,
|
| 66 |
+
"swiglu_limit": 7.0,
|
| 67 |
+
"tie_word_embeddings": false,
|
| 68 |
+
"torch_dtype": "bfloat16",
|
| 69 |
+
"transformers_version": "4.55.0",
|
| 70 |
+
"use_cache": false,
|
| 71 |
+
"vocab_size": 201088
|
| 72 |
+
}
|
.ipynb_checkpoints/generation_config-checkpoint.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 199998,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
200002,
|
| 6 |
+
199999,
|
| 7 |
+
200012
|
| 8 |
+
],
|
| 9 |
+
"pad_token_id": 199999,
|
| 10 |
+
"transformers_version": "4.55.0"
|
| 11 |
+
}
|
.ipynb_checkpoints/special_tokens_map-checkpoint.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|startoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|return|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
.ipynb_checkpoints/tokenizer-checkpoint.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0614fe83cadab421296e664e1f48f4261fa8fef6e03e63bb75c20f38e37d07d3
|
| 3 |
+
size 27868174
|
.ipynb_checkpoints/tokenizer_config-checkpoint.json
ADDED
|
@@ -0,0 +1,183 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"199998": {
|
| 4 |
+
"content": "<|startoftext|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"199999": {
|
| 12 |
+
"content": "<|endoftext|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"200000": {
|
| 20 |
+
"content": "<|reserved_200000|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"200001": {
|
| 28 |
+
"content": "<|reserved_200001|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"200002": {
|
| 36 |
+
"content": "<|return|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"200003": {
|
| 44 |
+
"content": "<|constrain|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"200004": {
|
| 52 |
+
"content": "<|reserved_200004|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"200005": {
|
| 60 |
+
"content": "<|channel|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"200006": {
|
| 68 |
+
"content": "<|start|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"200007": {
|
| 76 |
+
"content": "<|end|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"200008": {
|
| 84 |
+
"content": "<|message|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"200009": {
|
| 92 |
+
"content": "<|reserved_200009|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"200010": {
|
| 100 |
+
"content": "<|reserved_200010|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"200011": {
|
| 108 |
+
"content": "<|reserved_200011|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"200012": {
|
| 116 |
+
"content": "<|call|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"200013": {
|
| 124 |
+
"content": "<|reserved_200013|>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"200014": {
|
| 132 |
+
"content": "<|reserved_200014|>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"200015": {
|
| 140 |
+
"content": "<|reserved_200015|>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"200016": {
|
| 148 |
+
"content": "<|reserved_200016|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"200017": {
|
| 156 |
+
"content": "<|reserved_200017|>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"200018": {
|
| 164 |
+
"content": "<|endofprompt|>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
}
|
| 171 |
+
},
|
| 172 |
+
"bos_token": "<|startoftext|>",
|
| 173 |
+
"clean_up_tokenization_spaces": false,
|
| 174 |
+
"eos_token": "<|return|>",
|
| 175 |
+
"extra_special_tokens": {},
|
| 176 |
+
"model_input_names": [
|
| 177 |
+
"input_ids",
|
| 178 |
+
"attention_mask"
|
| 179 |
+
],
|
| 180 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 181 |
+
"pad_token": "<|endoftext|>",
|
| 182 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 183 |
+
}
|
.msc
ADDED
|
Binary file (2.15 kB). View file
|
|
|
.mv
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
Revision:master,CreatedAt:1758679619
|
README.md
CHANGED
|
@@ -1,3 +1,48 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags: []
|
| 4 |
+
|
| 5 |
+
#model-type:
|
| 6 |
+
##如 gpt、phi、llama、chatglm、baichuan 等
|
| 7 |
+
#- gpt
|
| 8 |
+
|
| 9 |
+
#domain:
|
| 10 |
+
##如 nlp、cv、audio、multi-modal
|
| 11 |
+
#- nlp
|
| 12 |
+
|
| 13 |
+
#language:
|
| 14 |
+
##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
|
| 15 |
+
#- cn
|
| 16 |
+
|
| 17 |
+
#metrics:
|
| 18 |
+
##如 CIDEr、Blue、ROUGE 等
|
| 19 |
+
#- CIDEr
|
| 20 |
+
|
| 21 |
+
#tags:
|
| 22 |
+
##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
|
| 23 |
+
#- pretrained
|
| 24 |
+
|
| 25 |
+
#tools:
|
| 26 |
+
##如 vllm、fastchat、llamacpp、AdaSeq 等
|
| 27 |
+
#- vllm
|
| 28 |
+
---
|
| 29 |
+
### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。
|
| 30 |
+
#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型
|
| 31 |
+
|
| 32 |
+
SDK下载
|
| 33 |
+
```bash
|
| 34 |
+
#安装ModelScope
|
| 35 |
+
pip install modelscope
|
| 36 |
+
```
|
| 37 |
+
```python
|
| 38 |
+
#SDK模型下载
|
| 39 |
+
from modelscope import snapshot_download
|
| 40 |
+
model_dir = snapshot_download('LambdaJder/JSL-joysafety-v1')
|
| 41 |
+
```
|
| 42 |
+
Git下载
|
| 43 |
+
```
|
| 44 |
+
#Git模型下载
|
| 45 |
+
git clone https://www.modelscope.cn/LambdaJder/JSL-joysafety-v1.git
|
| 46 |
+
```
|
| 47 |
+
|
| 48 |
+
<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>
|
args.json
ADDED
|
@@ -0,0 +1,379 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"output_dir": "./output",
|
| 3 |
+
"overwrite_output_dir": false,
|
| 4 |
+
"do_train": false,
|
| 5 |
+
"do_eval": false,
|
| 6 |
+
"do_predict": false,
|
| 7 |
+
"eval_strategy": "no",
|
| 8 |
+
"prediction_loss_only": false,
|
| 9 |
+
"per_device_train_batch_size": 1,
|
| 10 |
+
"per_device_eval_batch_size": 1,
|
| 11 |
+
"per_gpu_train_batch_size": null,
|
| 12 |
+
"per_gpu_eval_batch_size": null,
|
| 13 |
+
"gradient_accumulation_steps": 7,
|
| 14 |
+
"eval_accumulation_steps": null,
|
| 15 |
+
"eval_delay": 0,
|
| 16 |
+
"torch_empty_cache_steps": null,
|
| 17 |
+
"learning_rate": 5e-06,
|
| 18 |
+
"weight_decay": 0.1,
|
| 19 |
+
"adam_beta1": 0.9,
|
| 20 |
+
"adam_beta2": 0.95,
|
| 21 |
+
"adam_epsilon": 1e-08,
|
| 22 |
+
"max_grad_norm": 1.0,
|
| 23 |
+
"num_train_epochs": 6.0,
|
| 24 |
+
"max_steps": -1,
|
| 25 |
+
"lr_scheduler_type": "cosine",
|
| 26 |
+
"lr_scheduler_kwargs": null,
|
| 27 |
+
"warmup_ratio": 0.05,
|
| 28 |
+
"warmup_steps": 0,
|
| 29 |
+
"log_level": "passive",
|
| 30 |
+
"log_level_replica": "warning",
|
| 31 |
+
"log_on_each_node": true,
|
| 32 |
+
"logging_dir": "./output/logs",
|
| 33 |
+
"logging_strategy": "steps",
|
| 34 |
+
"logging_first_step": true,
|
| 35 |
+
"logging_steps": 5,
|
| 36 |
+
"logging_nan_inf_filter": true,
|
| 37 |
+
"save_strategy": "steps",
|
| 38 |
+
"save_steps": 1609.0,
|
| 39 |
+
"save_total_limit": 10,
|
| 40 |
+
"save_safetensors": true,
|
| 41 |
+
"save_on_each_node": false,
|
| 42 |
+
"save_only_model": false,
|
| 43 |
+
"restore_callback_states_from_checkpoint": false,
|
| 44 |
+
"no_cuda": false,
|
| 45 |
+
"use_cpu": false,
|
| 46 |
+
"use_mps_device": false,
|
| 47 |
+
"seed": 42,
|
| 48 |
+
"data_seed": 42,
|
| 49 |
+
"jit_mode_eval": false,
|
| 50 |
+
"use_ipex": false,
|
| 51 |
+
"bf16": true,
|
| 52 |
+
"fp16": false,
|
| 53 |
+
"fp16_opt_level": "O1",
|
| 54 |
+
"half_precision_backend": "auto",
|
| 55 |
+
"bf16_full_eval": false,
|
| 56 |
+
"fp16_full_eval": false,
|
| 57 |
+
"tf32": null,
|
| 58 |
+
"local_rank": 0,
|
| 59 |
+
"ddp_backend": null,
|
| 60 |
+
"tpu_num_cores": null,
|
| 61 |
+
"tpu_metrics_debug": false,
|
| 62 |
+
"debug": null,
|
| 63 |
+
"dataloader_drop_last": false,
|
| 64 |
+
"eval_steps": 1609.0,
|
| 65 |
+
"dataloader_num_workers": 192,
|
| 66 |
+
"dataloader_prefetch_factor": null,
|
| 67 |
+
"past_index": -1,
|
| 68 |
+
"run_name": "safety-model-training",
|
| 69 |
+
"disable_tqdm": null,
|
| 70 |
+
"remove_unused_columns": true,
|
| 71 |
+
"label_names": null,
|
| 72 |
+
"load_best_model_at_end": false,
|
| 73 |
+
"metric_for_best_model": "loss",
|
| 74 |
+
"greater_is_better": false,
|
| 75 |
+
"ignore_data_skip": false,
|
| 76 |
+
"fsdp": "",
|
| 77 |
+
"fsdp_min_num_params": 0,
|
| 78 |
+
"fsdp_config": null,
|
| 79 |
+
"fsdp_transformer_layer_cls_to_wrap": null,
|
| 80 |
+
"accelerator_config": {
|
| 81 |
+
"dispatch_batches": false
|
| 82 |
+
},
|
| 83 |
+
"deepspeed": {
|
| 84 |
+
"fp16": {
|
| 85 |
+
"enabled": "auto",
|
| 86 |
+
"loss_scale": 0,
|
| 87 |
+
"loss_scale_window": 1000,
|
| 88 |
+
"initial_scale_power": 16,
|
| 89 |
+
"hysteresis": 2,
|
| 90 |
+
"min_loss_scale": 1
|
| 91 |
+
},
|
| 92 |
+
"bf16": {
|
| 93 |
+
"enabled": "auto"
|
| 94 |
+
},
|
| 95 |
+
"zero_optimization": {
|
| 96 |
+
"stage": 3,
|
| 97 |
+
"offload_optimizer": {
|
| 98 |
+
"device": "none",
|
| 99 |
+
"pin_memory": true
|
| 100 |
+
},
|
| 101 |
+
"offload_param": {
|
| 102 |
+
"device": "none",
|
| 103 |
+
"pin_memory": true
|
| 104 |
+
},
|
| 105 |
+
"overlap_comm": false,
|
| 106 |
+
"contiguous_gradients": true,
|
| 107 |
+
"sub_group_size": 1000000000.0,
|
| 108 |
+
"reduce_bucket_size": "auto",
|
| 109 |
+
"zero_quantized_weights": false,
|
| 110 |
+
"zero_quantized_gradients": false,
|
| 111 |
+
"stage3_prefetch_bucket_size": "auto",
|
| 112 |
+
"stage3_param_persistence_threshold": "auto",
|
| 113 |
+
"stage3_max_live_parameters": 1000000000.0,
|
| 114 |
+
"stage3_max_reuse_distance": 1000000000.0,
|
| 115 |
+
"stage3_gather_16bit_weights_on_model_save": true
|
| 116 |
+
},
|
| 117 |
+
"gradient_accumulation_steps": "auto",
|
| 118 |
+
"gradient_clipping": "auto",
|
| 119 |
+
"steps_per_print": 2000,
|
| 120 |
+
"train_batch_size": "auto",
|
| 121 |
+
"train_micro_batch_size_per_gpu": "auto",
|
| 122 |
+
"wall_clock_breakdown": false
|
| 123 |
+
},
|
| 124 |
+
"label_smoothing_factor": 0.0,
|
| 125 |
+
"optim": "adamw_torch",
|
| 126 |
+
"optim_args": null,
|
| 127 |
+
"adafactor": false,
|
| 128 |
+
"group_by_length": false,
|
| 129 |
+
"length_column_name": "length",
|
| 130 |
+
"report_to": [
|
| 131 |
+
"tensorboard"
|
| 132 |
+
],
|
| 133 |
+
"ddp_find_unused_parameters": null,
|
| 134 |
+
"ddp_bucket_cap_mb": null,
|
| 135 |
+
"ddp_broadcast_buffers": null,
|
| 136 |
+
"dataloader_pin_memory": true,
|
| 137 |
+
"dataloader_persistent_workers": false,
|
| 138 |
+
"skip_memory_metrics": true,
|
| 139 |
+
"use_legacy_prediction_loop": false,
|
| 140 |
+
"push_to_hub": false,
|
| 141 |
+
"resume_from_checkpoint": null,
|
| 142 |
+
"hub_model_id": null,
|
| 143 |
+
"hub_strategy": "every_save",
|
| 144 |
+
"hub_token": null,
|
| 145 |
+
"hub_private_repo": null,
|
| 146 |
+
"hub_always_push": false,
|
| 147 |
+
"hub_revision": null,
|
| 148 |
+
"gradient_checkpointing": true,
|
| 149 |
+
"gradient_checkpointing_kwargs": null,
|
| 150 |
+
"include_inputs_for_metrics": false,
|
| 151 |
+
"include_for_metrics": [],
|
| 152 |
+
"eval_do_concat_batches": true,
|
| 153 |
+
"fp16_backend": "auto",
|
| 154 |
+
"push_to_hub_model_id": null,
|
| 155 |
+
"push_to_hub_organization": null,
|
| 156 |
+
"push_to_hub_token": null,
|
| 157 |
+
"mp_parameters": "",
|
| 158 |
+
"auto_find_batch_size": false,
|
| 159 |
+
"full_determinism": false,
|
| 160 |
+
"torchdynamo": null,
|
| 161 |
+
"ray_scope": "last",
|
| 162 |
+
"ddp_timeout": 18000000,
|
| 163 |
+
"torch_compile": false,
|
| 164 |
+
"torch_compile_backend": null,
|
| 165 |
+
"torch_compile_mode": null,
|
| 166 |
+
"include_tokens_per_second": false,
|
| 167 |
+
"include_num_input_tokens_seen": false,
|
| 168 |
+
"neftune_noise_alpha": null,
|
| 169 |
+
"optim_target_modules": null,
|
| 170 |
+
"batch_eval_metrics": false,
|
| 171 |
+
"eval_on_start": false,
|
| 172 |
+
"use_liger_kernel": false,
|
| 173 |
+
"liger_kernel_config": null,
|
| 174 |
+
"eval_use_gather_object": false,
|
| 175 |
+
"average_tokens_across_devices": true,
|
| 176 |
+
"sortish_sampler": false,
|
| 177 |
+
"predict_with_generate": false,
|
| 178 |
+
"generation_max_length": null,
|
| 179 |
+
"generation_num_beams": null,
|
| 180 |
+
"generation_config": null,
|
| 181 |
+
"vit_gradient_checkpointing": null,
|
| 182 |
+
"check_model": true,
|
| 183 |
+
"acc_strategy": "token",
|
| 184 |
+
"train_dataloader_shuffle": true,
|
| 185 |
+
"max_epochs": null,
|
| 186 |
+
"aligner_lr": null,
|
| 187 |
+
"vit_lr": null,
|
| 188 |
+
"optimizer": null,
|
| 189 |
+
"use_logits_to_keep": null,
|
| 190 |
+
"channels": null,
|
| 191 |
+
"ds3_gather_for_generation": true,
|
| 192 |
+
"metric_warmup_step": 0,
|
| 193 |
+
"fsdp_num": 1,
|
| 194 |
+
"acc_steps": 1,
|
| 195 |
+
"eval_use_evalscope": false,
|
| 196 |
+
"eval_dataset": [],
|
| 197 |
+
"eval_dataset_args": null,
|
| 198 |
+
"eval_limit": null,
|
| 199 |
+
"eval_generation_config": null,
|
| 200 |
+
"model": "JSL-joysafety-v1/gpt-oss-20b",
|
| 201 |
+
"model_type": null,
|
| 202 |
+
"model_revision": null,
|
| 203 |
+
"task_type": "causal_lm",
|
| 204 |
+
"torch_dtype": "bfloat16",
|
| 205 |
+
"attn_impl": "flash_attn",
|
| 206 |
+
"num_labels": null,
|
| 207 |
+
"problem_type": null,
|
| 208 |
+
"rope_scaling": {
|
| 209 |
+
"beta_fast": 32.0,
|
| 210 |
+
"beta_slow": 1.0,
|
| 211 |
+
"factor": 32.0,
|
| 212 |
+
"original_max_position_embeddings": 4096,
|
| 213 |
+
"rope_type": "yarn",
|
| 214 |
+
"truncate": false,
|
| 215 |
+
"type": "yarn"
|
| 216 |
+
},
|
| 217 |
+
"device_map": null,
|
| 218 |
+
"max_memory": {},
|
| 219 |
+
"local_repo_path": null,
|
| 220 |
+
"init_strategy": null,
|
| 221 |
+
"template": "default",
|
| 222 |
+
"system": null,
|
| 223 |
+
"max_length": 8192,
|
| 224 |
+
"truncation_strategy": "right",
|
| 225 |
+
"max_pixels": null,
|
| 226 |
+
"agent_template": null,
|
| 227 |
+
"norm_bbox": null,
|
| 228 |
+
"use_chat_template": true,
|
| 229 |
+
"padding_free": false,
|
| 230 |
+
"padding_side": "right",
|
| 231 |
+
"loss_scale": "default",
|
| 232 |
+
"sequence_parallel_size": 1,
|
| 233 |
+
"response_prefix": null,
|
| 234 |
+
"template_backend": "swift",
|
| 235 |
+
"dataset": [
|
| 236 |
+
"JSL-joysafety-v1/safety-dataset"
|
| 237 |
+
],
|
| 238 |
+
"val_dataset": [],
|
| 239 |
+
"split_dataset_ratio": 0.0,
|
| 240 |
+
"dataset_num_proc": 192,
|
| 241 |
+
"load_from_cache_file": true,
|
| 242 |
+
"dataset_shuffle": true,
|
| 243 |
+
"val_dataset_shuffle": false,
|
| 244 |
+
"streaming": false,
|
| 245 |
+
"interleave_prob": null,
|
| 246 |
+
"stopping_strategy": "first_exhausted",
|
| 247 |
+
"shuffle_buffer_size": 1000,
|
| 248 |
+
"download_mode": "reuse_dataset_if_exists",
|
| 249 |
+
"columns": {},
|
| 250 |
+
"strict": false,
|
| 251 |
+
"model_name": null,
|
| 252 |
+
"model_author": null,
|
| 253 |
+
"custom_dataset_info": [],
|
| 254 |
+
"quant_method": null,
|
| 255 |
+
"quant_bits": null,
|
| 256 |
+
"hqq_axis": null,
|
| 257 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
| 258 |
+
"bnb_4bit_quant_type": "nf4",
|
| 259 |
+
"bnb_4bit_use_double_quant": true,
|
| 260 |
+
"bnb_4bit_quant_storage": null,
|
| 261 |
+
"max_new_tokens": 64,
|
| 262 |
+
"temperature": 0.0,
|
| 263 |
+
"top_k": null,
|
| 264 |
+
"top_p": null,
|
| 265 |
+
"repetition_penalty": null,
|
| 266 |
+
"num_beams": 1,
|
| 267 |
+
"stream": false,
|
| 268 |
+
"stop_words": [],
|
| 269 |
+
"logprobs": false,
|
| 270 |
+
"top_logprobs": null,
|
| 271 |
+
"ckpt_dir": null,
|
| 272 |
+
"lora_modules": [],
|
| 273 |
+
"tuner_backend": "peft",
|
| 274 |
+
"train_type": "full",
|
| 275 |
+
"adapters": [],
|
| 276 |
+
"external_plugins": [],
|
| 277 |
+
"model_kwargs": {},
|
| 278 |
+
"load_args": false,
|
| 279 |
+
"load_data_args": false,
|
| 280 |
+
"packing": false,
|
| 281 |
+
"packing_cache": null,
|
| 282 |
+
"custom_register_path": [],
|
| 283 |
+
"use_hf": false,
|
| 284 |
+
"ignore_args_error": false,
|
| 285 |
+
"use_swift_lora": false,
|
| 286 |
+
"freeze_parameters": [],
|
| 287 |
+
"freeze_parameters_regex": null,
|
| 288 |
+
"freeze_parameters_ratio": 0.0,
|
| 289 |
+
"trainable_parameters": [],
|
| 290 |
+
"trainable_parameters_regex": null,
|
| 291 |
+
"freeze_llm": false,
|
| 292 |
+
"freeze_vit": true,
|
| 293 |
+
"freeze_aligner": true,
|
| 294 |
+
"target_modules": [
|
| 295 |
+
"all-linear"
|
| 296 |
+
],
|
| 297 |
+
"target_regex": null,
|
| 298 |
+
"modules_to_save": [],
|
| 299 |
+
"lora_rank": 8,
|
| 300 |
+
"lora_alpha": 32,
|
| 301 |
+
"lora_dropout": 0.05,
|
| 302 |
+
"lora_bias": "none",
|
| 303 |
+
"lora_dtype": null,
|
| 304 |
+
"lorap_lr_ratio": null,
|
| 305 |
+
"use_rslora": false,
|
| 306 |
+
"use_dora": false,
|
| 307 |
+
"lora_ga_batch_size": 2,
|
| 308 |
+
"lora_ga_iters": 2,
|
| 309 |
+
"lora_ga_max_length": 1024,
|
| 310 |
+
"lora_ga_direction": "ArB2r",
|
| 311 |
+
"lora_ga_scale": "stable",
|
| 312 |
+
"lora_ga_stable_gamma": 16,
|
| 313 |
+
"init_weights": true,
|
| 314 |
+
"fourier_n_frequency": 2000,
|
| 315 |
+
"fourier_scaling": 300.0,
|
| 316 |
+
"boft_block_size": 4,
|
| 317 |
+
"boft_block_num": 0,
|
| 318 |
+
"boft_n_butterfly_factor": 1,
|
| 319 |
+
"boft_dropout": 0.0,
|
| 320 |
+
"vera_rank": 256,
|
| 321 |
+
"vera_projection_prng_key": 0,
|
| 322 |
+
"vera_dropout": 0.0,
|
| 323 |
+
"vera_d_initial": 0.1,
|
| 324 |
+
"adapter_act": "gelu",
|
| 325 |
+
"adapter_length": 128,
|
| 326 |
+
"use_galore": false,
|
| 327 |
+
"galore_target_modules": null,
|
| 328 |
+
"galore_rank": 128,
|
| 329 |
+
"galore_update_proj_gap": 50,
|
| 330 |
+
"galore_scale": 1.0,
|
| 331 |
+
"galore_proj_type": "std",
|
| 332 |
+
"galore_optim_per_parameter": false,
|
| 333 |
+
"galore_with_embedding": false,
|
| 334 |
+
"galore_quantization": false,
|
| 335 |
+
"galore_proj_quant": false,
|
| 336 |
+
"galore_proj_bits": 4,
|
| 337 |
+
"galore_proj_group_size": 256,
|
| 338 |
+
"galore_cos_threshold": 0.4,
|
| 339 |
+
"galore_gamma_proj": 2,
|
| 340 |
+
"galore_queue_size": 5,
|
| 341 |
+
"adalora_target_r": 8,
|
| 342 |
+
"adalora_init_r": 12,
|
| 343 |
+
"adalora_tinit": 0,
|
| 344 |
+
"adalora_tfinal": 0,
|
| 345 |
+
"adalora_deltaT": 1,
|
| 346 |
+
"adalora_beta1": 0.85,
|
| 347 |
+
"adalora_beta2": 0.85,
|
| 348 |
+
"adalora_orth_reg_weight": 0.5,
|
| 349 |
+
"llamapro_num_new_blocks": 4,
|
| 350 |
+
"llamapro_num_groups": null,
|
| 351 |
+
"lisa_activated_layers": 0,
|
| 352 |
+
"lisa_step_interval": 20,
|
| 353 |
+
"reft_layer_key": null,
|
| 354 |
+
"reft_layers": null,
|
| 355 |
+
"reft_rank": 4,
|
| 356 |
+
"reft_intervention_type": "LoreftIntervention",
|
| 357 |
+
"reft_args": null,
|
| 358 |
+
"swanlab_token": null,
|
| 359 |
+
"swanlab_project": null,
|
| 360 |
+
"swanlab_workspace": null,
|
| 361 |
+
"swanlab_exp_name": null,
|
| 362 |
+
"swanlab_lark_webhook_url": null,
|
| 363 |
+
"swanlab_lark_secret": null,
|
| 364 |
+
"swanlab_mode": "cloud",
|
| 365 |
+
"add_version": true,
|
| 366 |
+
"resume_only_model": false,
|
| 367 |
+
"create_checkpoint_symlink": false,
|
| 368 |
+
"lazy_tokenize": false,
|
| 369 |
+
"loss_type": null,
|
| 370 |
+
"metric": null,
|
| 371 |
+
"zero_hpz_partition_size": null,
|
| 372 |
+
"rank": 0,
|
| 373 |
+
"global_world_size": 40,
|
| 374 |
+
"local_world_size": 8,
|
| 375 |
+
"model_suffix": "gpt-oss-20b",
|
| 376 |
+
"model_meta": "ModelMeta(model_type=None, model_groups=[], template='dummy', get_function=<function get_model_tokenizer_from_local at 0x7f67a0a7b130>, model_arch=None, architectures=[], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, task_type=None, ignore_patterns=None, requires=[], tags=[])",
|
| 377 |
+
"model_dir": "/mnt/workspace/public_model/gpt-oss-20b",
|
| 378 |
+
"evaluation_strategy": "steps"
|
| 379 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,331 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{#-
|
| 2 |
+
In addition to the normal inputs of `messages` and `tools`, this template also accepts the
|
| 3 |
+
following kwargs:
|
| 4 |
+
- "builtin_tools": A list, can contain "browser" and/or "python".
|
| 5 |
+
- "model_identity": A string that optionally describes the model identity.
|
| 6 |
+
- "reasoning_effort": A string that describes the reasoning effort, defaults to "medium".
|
| 7 |
+
#}
|
| 8 |
+
|
| 9 |
+
{#- Tool Definition Rendering ============================================== #}
|
| 10 |
+
{%- macro render_typescript_type(param_spec, required_params, is_nullable=false) -%}
|
| 11 |
+
{%- if param_spec.type == "array" -%}
|
| 12 |
+
{%- if param_spec['items'] -%}
|
| 13 |
+
{%- if param_spec['items']['type'] == "string" -%}
|
| 14 |
+
{{- "string[]" }}
|
| 15 |
+
{%- elif param_spec['items']['type'] == "number" -%}
|
| 16 |
+
{{- "number[]" }}
|
| 17 |
+
{%- elif param_spec['items']['type'] == "integer" -%}
|
| 18 |
+
{{- "number[]" }}
|
| 19 |
+
{%- elif param_spec['items']['type'] == "boolean" -%}
|
| 20 |
+
{{- "boolean[]" }}
|
| 21 |
+
{%- else -%}
|
| 22 |
+
{%- set inner_type = render_typescript_type(param_spec['items'], required_params) -%}
|
| 23 |
+
{%- if inner_type == "object | object" or inner_type|length > 50 -%}
|
| 24 |
+
{{- "any[]" }}
|
| 25 |
+
{%- else -%}
|
| 26 |
+
{{- inner_type + "[]" }}
|
| 27 |
+
{%- endif -%}
|
| 28 |
+
{%- endif -%}
|
| 29 |
+
{%- if param_spec.nullable -%}
|
| 30 |
+
{{- " | null" }}
|
| 31 |
+
{%- endif -%}
|
| 32 |
+
{%- else -%}
|
| 33 |
+
{{- "any[]" }}
|
| 34 |
+
{%- if param_spec.nullable -%}
|
| 35 |
+
{{- " | null" }}
|
| 36 |
+
{%- endif -%}
|
| 37 |
+
{%- endif -%}
|
| 38 |
+
{%- elif param_spec.type is defined and param_spec.type is iterable and param_spec.type is not string and param_spec.type is not mapping and param_spec.type[0] is defined -%}
|
| 39 |
+
{#- Handle array of types like ["object", "object"] from Union[dict, list] #}
|
| 40 |
+
{%- if param_spec.type | length > 1 -%}
|
| 41 |
+
{{- param_spec.type | join(" | ") }}
|
| 42 |
+
{%- else -%}
|
| 43 |
+
{{- param_spec.type[0] }}
|
| 44 |
+
{%- endif -%}
|
| 45 |
+
{%- elif param_spec.oneOf -%}
|
| 46 |
+
{#- Handle oneOf schemas - check for complex unions and fallback to any #}
|
| 47 |
+
{%- set has_object_variants = false -%}
|
| 48 |
+
{%- for variant in param_spec.oneOf -%}
|
| 49 |
+
{%- if variant.type == "object" -%}
|
| 50 |
+
{%- set has_object_variants = true -%}
|
| 51 |
+
{%- endif -%}
|
| 52 |
+
{%- endfor -%}
|
| 53 |
+
{%- if has_object_variants and param_spec.oneOf|length > 1 -%}
|
| 54 |
+
{{- "any" }}
|
| 55 |
+
{%- else -%}
|
| 56 |
+
{%- for variant in param_spec.oneOf -%}
|
| 57 |
+
{{- render_typescript_type(variant, required_params) -}}
|
| 58 |
+
{%- if variant.description %}
|
| 59 |
+
{{- "// " + variant.description }}
|
| 60 |
+
{%- endif -%}
|
| 61 |
+
{%- if variant.default is defined %}
|
| 62 |
+
{{ "// default: " + variant.default|tojson }}
|
| 63 |
+
{%- endif -%}
|
| 64 |
+
{%- if not loop.last %}
|
| 65 |
+
{{- " | " }}
|
| 66 |
+
{% endif -%}
|
| 67 |
+
{%- endfor -%}
|
| 68 |
+
{%- endif -%}
|
| 69 |
+
{%- elif param_spec.type == "string" -%}
|
| 70 |
+
{%- if param_spec.enum -%}
|
| 71 |
+
{{- '"' + param_spec.enum|join('" | "') + '"' -}}
|
| 72 |
+
{%- else -%}
|
| 73 |
+
{{- "string" }}
|
| 74 |
+
{%- if param_spec.nullable %}
|
| 75 |
+
{{- " | null" }}
|
| 76 |
+
{%- endif -%}
|
| 77 |
+
{%- endif -%}
|
| 78 |
+
{%- elif param_spec.type == "number" -%}
|
| 79 |
+
{{- "number" }}
|
| 80 |
+
{%- elif param_spec.type == "integer" -%}
|
| 81 |
+
{{- "number" }}
|
| 82 |
+
{%- elif param_spec.type == "boolean" -%}
|
| 83 |
+
{{- "boolean" }}
|
| 84 |
+
|
| 85 |
+
{%- elif param_spec.type == "object" -%}
|
| 86 |
+
{%- if param_spec.properties -%}
|
| 87 |
+
{{- "{\n" }}
|
| 88 |
+
{%- for prop_name, prop_spec in param_spec.properties.items() -%}
|
| 89 |
+
{{- prop_name -}}
|
| 90 |
+
{%- if prop_name not in (param_spec.required or []) -%}
|
| 91 |
+
{{- "?" }}
|
| 92 |
+
{%- endif -%}
|
| 93 |
+
{{- ": " }}
|
| 94 |
+
{{ render_typescript_type(prop_spec, param_spec.required or []) }}
|
| 95 |
+
{%- if not loop.last -%}
|
| 96 |
+
{{-", " }}
|
| 97 |
+
{%- endif -%}
|
| 98 |
+
{%- endfor -%}
|
| 99 |
+
{{- "}" }}
|
| 100 |
+
{%- else -%}
|
| 101 |
+
{{- "object" }}
|
| 102 |
+
{%- endif -%}
|
| 103 |
+
{%- else -%}
|
| 104 |
+
{{- "any" }}
|
| 105 |
+
{%- endif -%}
|
| 106 |
+
{%- endmacro -%}
|
| 107 |
+
|
| 108 |
+
{%- macro render_tool_namespace(namespace_name, tools) -%}
|
| 109 |
+
{{- "## " + namespace_name + "\n\n" }}
|
| 110 |
+
{{- "namespace " + namespace_name + " {\n\n" }}
|
| 111 |
+
{%- for tool in tools %}
|
| 112 |
+
{%- set tool = tool.function %}
|
| 113 |
+
{{- "// " + tool.description + "\n" }}
|
| 114 |
+
{{- "type "+ tool.name + " = " }}
|
| 115 |
+
{%- if tool.parameters and tool.parameters.properties %}
|
| 116 |
+
{{- "(_: {\n" }}
|
| 117 |
+
{%- for param_name, param_spec in tool.parameters.properties.items() %}
|
| 118 |
+
{%- if param_spec.description %}
|
| 119 |
+
{{- "// " + param_spec.description + "\n" }}
|
| 120 |
+
{%- endif %}
|
| 121 |
+
{{- param_name }}
|
| 122 |
+
{%- if param_name not in (tool.parameters.required or []) -%}
|
| 123 |
+
{{- "?" }}
|
| 124 |
+
{%- endif -%}
|
| 125 |
+
{{- ": " }}
|
| 126 |
+
{{- render_typescript_type(param_spec, tool.parameters.required or []) }}
|
| 127 |
+
{%- if param_spec.default is defined -%}
|
| 128 |
+
{%- if param_spec.enum %}
|
| 129 |
+
{{- ", // default: " + param_spec.default }}
|
| 130 |
+
{%- elif param_spec.oneOf %}
|
| 131 |
+
{{- "// default: " + param_spec.default }}
|
| 132 |
+
{%- else %}
|
| 133 |
+
{{- ", // default: " + param_spec.default|tojson }}
|
| 134 |
+
{%- endif -%}
|
| 135 |
+
{%- endif -%}
|
| 136 |
+
{%- if not loop.last %}
|
| 137 |
+
{{- ",\n" }}
|
| 138 |
+
{%- else %}
|
| 139 |
+
{{- ",\n" }}
|
| 140 |
+
{%- endif -%}
|
| 141 |
+
{%- endfor %}
|
| 142 |
+
{{- "}) => any;\n\n" }}
|
| 143 |
+
{%- else -%}
|
| 144 |
+
{{- "() => any;\n\n" }}
|
| 145 |
+
{%- endif -%}
|
| 146 |
+
{%- endfor %}
|
| 147 |
+
{{- "} // namespace " + namespace_name }}
|
| 148 |
+
{%- endmacro -%}
|
| 149 |
+
|
| 150 |
+
{%- macro render_builtin_tools(browser_tool, python_tool) -%}
|
| 151 |
+
{%- if browser_tool %}
|
| 152 |
+
{{- "## browser\n\n" }}
|
| 153 |
+
{{- "// Tool for browsing.\n" }}
|
| 154 |
+
{{- "// The `cursor` appears in brackets before each browsing display: `[{cursor}]`.\n" }}
|
| 155 |
+
{{- "// Cite information from the tool using the following format:\n" }}
|
| 156 |
+
{{- "// `【{cursor}†L{line_start}(-L{line_end})?】`, for example: `【6†L9-L11】` or `【8†L3】`.\n" }}
|
| 157 |
+
{{- "// Do not quote more than 10 words directly from the tool output.\n" }}
|
| 158 |
+
{{- "// sources=web (default: web)\n" }}
|
| 159 |
+
{{- "namespace browser {\n\n" }}
|
| 160 |
+
{{- "// Searches for information related to `query` and displays `topn` results.\n" }}
|
| 161 |
+
{{- "type search = (_: {\n" }}
|
| 162 |
+
{{- "query: string,\n" }}
|
| 163 |
+
{{- "topn?: number, // default: 10\n" }}
|
| 164 |
+
{{- "source?: string,\n" }}
|
| 165 |
+
{{- "}) => any;\n\n" }}
|
| 166 |
+
{{- "// Opens the link `id` from the page indicated by `cursor` starting at line number `loc`, showing `num_lines` lines.\n" }}
|
| 167 |
+
{{- "// Valid link ids are displayed with the formatting: `【{id}†.*】`.\n" }}
|
| 168 |
+
{{- "// If `cursor` is not provided, the most recent page is implied.\n" }}
|
| 169 |
+
{{- "// If `id` is a string, it is treated as a fully qualified URL associated with `source`.\n" }}
|
| 170 |
+
{{- "// If `loc` is not provided, the viewport will be positioned at the beginning of the document or centered on the most relevant passage, if available.\n" }}
|
| 171 |
+
{{- "// Use this function without `id` to scroll to a new location of an opened page.\n" }}
|
| 172 |
+
{{- "type open = (_: {\n" }}
|
| 173 |
+
{{- "id?: number | string, // default: -1\n" }}
|
| 174 |
+
{{- "cursor?: number, // default: -1\n" }}
|
| 175 |
+
{{- "loc?: number, // default: -1\n" }}
|
| 176 |
+
{{- "num_lines?: number, // default: -1\n" }}
|
| 177 |
+
{{- "view_source?: boolean, // default: false\n" }}
|
| 178 |
+
{{- "source?: string,\n" }}
|
| 179 |
+
{{- "}) => any;\n\n" }}
|
| 180 |
+
{{- "// Finds exact matches of `pattern` in the current page, or the page given by `cursor`.\n" }}
|
| 181 |
+
{{- "type find = (_: {\n" }}
|
| 182 |
+
{{- "pattern: string,\n" }}
|
| 183 |
+
{{- "cursor?: number, // default: -1\n" }}
|
| 184 |
+
{{- "}) => any;\n\n" }}
|
| 185 |
+
{{- "} // namespace browser\n\n" }}
|
| 186 |
+
{%- endif -%}
|
| 187 |
+
|
| 188 |
+
{%- if python_tool %}
|
| 189 |
+
{{- "## python\n\n" }}
|
| 190 |
+
{{- "Use this tool to execute Python code in your chain of thought. The code will not be shown to the user. This tool should be used for internal reasoning, but not for code that is intended to be visible to the user (e.g. when creating plots, tables, or files).\n\n" }}
|
| 191 |
+
{{- "When you send a message containing Python code to python, it will be executed in a stateful Jupyter notebook environment. python will respond with the output of the execution or time out after 120.0 seconds. The drive at '/mnt/data' can be used to save and persist user files. Internet access for this session is UNKNOWN. Depends on the cluster.\n\n" }}
|
| 192 |
+
{%- endif -%}
|
| 193 |
+
{%- endmacro -%}
|
| 194 |
+
|
| 195 |
+
{#- System Message Construction ============================================ #}
|
| 196 |
+
{%- macro build_system_message() -%}
|
| 197 |
+
{%- if model_identity is not defined %}
|
| 198 |
+
{%- set model_identity = "\n\n你是一名「大模型内容安全审核专家」，请根据下面的风险审核checklist完成风险审核;\n\n#【任务描述】:\n\n 在 AI 对话场景中，完成用户输入与大模型回答安全审核，识别其中是否存在风险内容及诱导性风险。\n \n# 【注意事项】:\n 1. 按照《生成式人工智能服务管理暂行办法》进行风险审核； \n 2. 输出仅返回 JSON，不要附加任何解释性文字。 \n\n# 【风险审核-checklist】:\n\n 判断用户输入是否存在以下风险类型：涉政、暴恐、涉黄、涉赌、涉毒、辱骂、违禁、歧视、其他侵犯他人权益、其他商业违法违规等相关风险；无任何风险则归类为“正常文本”\n\n**输出格式**（JSON，禁止省略任何字段）：\n\n```json\n{\n \"reason\":\"cot分析过程\",\n \"risk_level\": 无风险|低风险|中风险|高风险, \n \"hit_categories\": [\"****\",\"****:],\n \"hit_detaile_categories\":[\"****\",\"****\"]\n \"risk_tags\"[] \n \"risk_roler\":\"user|\"ai\"|\"user&ai\",\n \"hit_keywords\": [\"xxx\"], \n \"suggestion\": \"pass\"|\"mask\"|\"block\"|\"review\"|\"proxy_answer\"\n}\n```\n**输出格式声明**\n reason:存放推理过程；\n risk_level:存放风险级别，分成四档:无风险|低风险|中风险|高风险；\n hit_categories:存放识别到的一级风险类别标签；\n hit_detaile_categories:存放识别到的二级风险类别标签；\n risk_tags:详细风险类型；\n risk_roler:存放对话中触发风险角色，user代表用户输入有风险，user&ai代表用户输入大模型回复都有风险，ai代表大模型回复有风险；\n hit_keywords:触发风险的原文片段；\n suggestion:建议处置策略；\n" %}
|
| 199 |
+
{%- endif %}
|
| 200 |
+
{{- model_identity + "\n" }}
|
| 201 |
+
{{- "Knowledge cutoff: 2024-06\n" }}
|
| 202 |
+
{{- "Current date: " + strftime_now("%Y-%m-%d") + "\n\n" }}
|
| 203 |
+
{%- if reasoning_effort is not defined %}
|
| 204 |
+
{%- set reasoning_effort = "medium" %}
|
| 205 |
+
{%- endif %}
|
| 206 |
+
{{- "Reasoning: " + reasoning_effort + "\n\n" }}
|
| 207 |
+
{%- if builtin_tools %}
|
| 208 |
+
{{- "# Tools\n\n" }}
|
| 209 |
+
{%- set available_builtin_tools = namespace(browser=false, python=false) %}
|
| 210 |
+
{%- for tool in builtin_tools %}
|
| 211 |
+
{%- if tool == "browser" %}
|
| 212 |
+
{%- set available_builtin_tools.browser = true %}
|
| 213 |
+
{%- elif tool == "python" %}
|
| 214 |
+
{%- set available_builtin_tools.python = true %}
|
| 215 |
+
{%- endif %}
|
| 216 |
+
{%- endfor %}
|
| 217 |
+
{{- render_builtin_tools(available_builtin_tools.browser, available_builtin_tools.python) }}
|
| 218 |
+
{%- endif -%}
|
| 219 |
+
{{- "# Valid channels: analysis, commentary, final. Channel must be included for every message." }}
|
| 220 |
+
{%- if tools -%}
|
| 221 |
+
{{- "\nCalls to these tools must go to the commentary channel: 'functions'." }}
|
| 222 |
+
{%- endif -%}
|
| 223 |
+
{%- endmacro -%}
|
| 224 |
+
|
| 225 |
+
{#- Main Template Logic ================================================= #}
|
| 226 |
+
{#- Set defaults #}
|
| 227 |
+
|
| 228 |
+
{#- Render system message #}
|
| 229 |
+
{{- "<|start|>system<|message|>" }}
|
| 230 |
+
{{- build_system_message() }}
|
| 231 |
+
{{- "<|end|>" }}
|
| 232 |
+
|
| 233 |
+
{#- Extract developer message #}
|
| 234 |
+
{%- if messages[0].role == "developer" or messages[0].role == "system" %}
|
| 235 |
+
{%- set developer_message = messages[0].content %}
|
| 236 |
+
{%- set loop_messages = messages[1:] %}
|
| 237 |
+
{%- else %}
|
| 238 |
+
{%- set developer_message = "" %}
|
| 239 |
+
{%- set loop_messages = messages %}
|
| 240 |
+
{%- endif %}
|
| 241 |
+
|
| 242 |
+
{#- Render developer message #}
|
| 243 |
+
{%- if developer_message or tools %}
|
| 244 |
+
{{- "<|start|>developer<|message|>" }}
|
| 245 |
+
{%- if developer_message %}
|
| 246 |
+
{{- "# Instructions\n\n" }}
|
| 247 |
+
{{- developer_message }}
|
| 248 |
+
{{- "\n\n" }}
|
| 249 |
+
{%- endif %}
|
| 250 |
+
{%- if tools -%}
|
| 251 |
+
{{- "# Tools\n\n" }}
|
| 252 |
+
{{- render_tool_namespace("functions", tools) }}
|
| 253 |
+
{%- endif -%}
|
| 254 |
+
{{- "<|end|>" }}
|
| 255 |
+
{%- endif %}
|
| 256 |
+
|
| 257 |
+
{#- Render messages #}
|
| 258 |
+
{%- set last_tool_call = namespace(name=none) %}
|
| 259 |
+
{%- for message in loop_messages -%}
|
| 260 |
+
{#- At this point only assistant/user/tool messages should remain #}
|
| 261 |
+
{%- if message.role == 'assistant' -%}
|
| 262 |
+
{#- Checks to ensure the messages are being passed in the format we expect #}
|
| 263 |
+
{%- if "content" in message %}
|
| 264 |
+
{%- if "<|channel|>analysis<|message|>" in message.content or "<|channel|>final<|message|>" in message.content %}
|
| 265 |
+
{{- raise_exception("You have passed a message containing <|channel|> tags in the content field. Instead of doing this, you should pass analysis messages (the string between '<|message|>' and '<|end|>') in the 'thinking' field, and final messages (the string between '<|message|>' and '<|end|>') in the 'content' field.") }}
|
| 266 |
+
{%- endif %}
|
| 267 |
+
{%- endif %}
|
| 268 |
+
{%- if "thinking" in message %}
|
| 269 |
+
{%- if "<|channel|>analysis<|message|>" in message.thinking or "<|channel|>final<|message|>" in message.thinking %}
|
| 270 |
+
{{- raise_exception("You have passed a message containing <|channel|> tags in the thinking field. Instead of doing this, you should pass analysis messages (the string between '<|message|>' and '<|end|>') in the 'thinking' field, and final messages (the string between '<|message|>' and '<|end|>') in the 'content' field.") }}
|
| 271 |
+
{%- endif %}
|
| 272 |
+
{%- endif %}
|
| 273 |
+
{%- if "tool_calls" in message %}
|
| 274 |
+
{#- We need very careful handling here - we want to drop the tool call analysis message if the model #}
|
| 275 |
+
{#- has output a later <|final|> message, but otherwise we want to retain it. This is the only case #}
|
| 276 |
+
{#- when we render CoT/analysis messages in inference. #}
|
| 277 |
+
{%- set future_final_message = namespace(found=false) %}
|
| 278 |
+
{%- for future_message in loop_messages[loop.index:] %}
|
| 279 |
+
{%- if future_message.role == 'assistant' and "tool_calls" not in future_message %}
|
| 280 |
+
{%- set future_final_message.found = true %}
|
| 281 |
+
{%- endif %}
|
| 282 |
+
{%- endfor %}
|
| 283 |
+
{#- We assume max 1 tool call per message, and so we infer the tool call name #}
|
| 284 |
+
{#- in "tool" messages from the most recent assistant tool call name #}
|
| 285 |
+
{%- set tool_call = message.tool_calls[0] %}
|
| 286 |
+
{%- if tool_call.function %}
|
| 287 |
+
{%- set tool_call = tool_call.function %}
|
| 288 |
+
{%- endif %}
|
| 289 |
+
{%- if message.content and message.thinking %}
|
| 290 |
+
{{- raise_exception("Cannot pass both content and thinking in an assistant message with tool calls! Put the analysis message in one or the other, but not both.") }}
|
| 291 |
+
{%- elif message.content and not future_final_message.found %}
|
| 292 |
+
{{- "<|start|>assistant<|channel|>analysis<|message|>" + message.content + "<|end|>" }}
|
| 293 |
+
{%- elif message.thinking and not future_final_message.found %}
|
| 294 |
+
{{- "<|start|>assistant<|channel|>analysis<|message|>" + message.thinking + "<|end|>" }}
|
| 295 |
+
{%- endif %}
|
| 296 |
+
{{- "<|start|>assistant to=" }}
|
| 297 |
+
{{- "functions." + tool_call.name + "<|channel|>commentary " }}
|
| 298 |
+
{{- (tool_call.content_type if tool_call.content_type is defined else "json") + "<|message|>" }}
|
| 299 |
+
{{- tool_call.arguments|tojson }}
|
| 300 |
+
{{- "<|call|>" }}
|
| 301 |
+
{%- set last_tool_call.name = tool_call.name %}
|
| 302 |
+
{%- elif loop.last and not add_generation_prompt %}
|
| 303 |
+
{#- Only render the CoT if the final turn is an assistant turn and add_generation_prompt is false #}
|
| 304 |
+
{#- This is a situation that should only occur in training, never in inference. #}
|
| 305 |
+
{%- if "thinking" in message %}
|
| 306 |
+
{{- "<|start|>assistant<|channel|>analysis<|message|>" + message.thinking + "<|end|>" }}
|
| 307 |
+
{%- endif %}
|
| 308 |
+
{#- <|return|> indicates the end of generation, but <|end|> does not #}
|
| 309 |
+
{#- <|return|> should never be an input to the model, but we include it as the final token #}
|
| 310 |
+
{#- when training, so the model learns to emit it. #}
|
| 311 |
+
{{- "<|start|>assistant<|channel|>final<|message|>" + message.content + "<|return|>" }}
|
| 312 |
+
{%- else %}
|
| 313 |
+
{#- CoT is dropped during all previous turns, so we never render it for inference #}
|
| 314 |
+
{{- "<|start|>assistant<|channel|>final<|message|>" + message.content + "<|end|>" }}
|
| 315 |
+
{%- set last_tool_call.name = none %}
|
| 316 |
+
{%- endif %}
|
| 317 |
+
{%- elif message.role == 'tool' -%}
|
| 318 |
+
{%- if last_tool_call.name is none %}
|
| 319 |
+
{{- raise_exception("Message has tool role, but there was no previous assistant message with a tool call!") }}
|
| 320 |
+
{%- endif %}
|
| 321 |
+
{{- "<|start|>functions." + last_tool_call.name }}
|
| 322 |
+
{{- " to=assistant<|channel|>commentary<|message|>" + message.content|tojson + "<|end|>" }}
|
| 323 |
+
{%- elif message.role == 'user' -%}
|
| 324 |
+
{{- "<|start|>user<|message|>" + message.content + "<|end|>" }}
|
| 325 |
+
{%- endif -%}
|
| 326 |
+
{%- endfor -%}
|
| 327 |
+
|
| 328 |
+
{#- Generation prompt #}
|
| 329 |
+
{%- if add_generation_prompt -%}
|
| 330 |
+
<|start|>assistant
|
| 331 |
+
{%- endif -%}
|
config.json
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"GptOssForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": true,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"eos_token_id": 200002,
|
| 8 |
+
"experts_per_token": 4,
|
| 9 |
+
"head_dim": 64,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2880,
|
| 12 |
+
"initial_context_length": 4096,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 2880,
|
| 15 |
+
"keys_to_ignore_at_inference": [
|
| 16 |
+
"past_key_values"
|
| 17 |
+
],
|
| 18 |
+
"layer_types": [
|
| 19 |
+
"sliding_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"sliding_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"sliding_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"sliding_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"sliding_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"sliding_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"sliding_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"sliding_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"sliding_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"sliding_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"sliding_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"sliding_attention",
|
| 42 |
+
"full_attention"
|
| 43 |
+
],
|
| 44 |
+
"max_position_embeddings": 131072,
|
| 45 |
+
"model_type": "gpt_oss",
|
| 46 |
+
"num_attention_heads": 64,
|
| 47 |
+
"num_experts_per_tok": 4,
|
| 48 |
+
"num_hidden_layers": 24,
|
| 49 |
+
"num_key_value_heads": 8,
|
| 50 |
+
"num_local_experts": 32,
|
| 51 |
+
"output_router_logits": false,
|
| 52 |
+
"pad_token_id": 199999,
|
| 53 |
+
"rms_norm_eps": 1e-05,
|
| 54 |
+
"rope_scaling": {
|
| 55 |
+
"beta_fast": 32.0,
|
| 56 |
+
"beta_slow": 1.0,
|
| 57 |
+
"factor": 32.0,
|
| 58 |
+
"original_max_position_embeddings": 4096,
|
| 59 |
+
"rope_type": "yarn",
|
| 60 |
+
"truncate": false,
|
| 61 |
+
"type": "yarn"
|
| 62 |
+
},
|
| 63 |
+
"rope_theta": 150000,
|
| 64 |
+
"router_aux_loss_coef": 0.9,
|
| 65 |
+
"sliding_window": 128,
|
| 66 |
+
"swiglu_limit": 7.0,
|
| 67 |
+
"tie_word_embeddings": false,
|
| 68 |
+
"torch_dtype": "bfloat16",
|
| 69 |
+
"transformers_version": "4.55.0",
|
| 70 |
+
"use_cache": false,
|
| 71 |
+
"vocab_size": 201088
|
| 72 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 199998,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
200002,
|
| 6 |
+
199999,
|
| 7 |
+
200012
|
| 8 |
+
],
|
| 9 |
+
"pad_token_id": 199999,
|
| 10 |
+
"transformers_version": "4.55.0"
|
| 11 |
+
}
|
model-00001-of-00009.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e4f08c59c38b2fa93484c5bb6a1138e42b02c0b6b8180c9eba84891145626fae
|
| 3 |
+
size 4504304664
|
model-00002-of-00009.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a076be34a28432f3addaf17d8d59050bc1570355220128ea9db099fb7bdf328
|
| 3 |
+
size 4939127656
|
model-00003-of-00009.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30612274cf8509bd0dee0dfd5d3bdce9a9390654dff92cda0899065b2d20537d
|
| 3 |
+
size 4939127656
|
model-00004-of-00009.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ae42d901748571cc4d7c19c04a3b2090e0bd5294a78dc673d01baa27e9c41a0
|
| 3 |
+
size 4939127680
|
model-00005-of-00009.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:009c996fb55d035f2a7e68854b5ff6bf419976213399bf024a5bca01acf21e36
|
| 3 |
+
size 4939127704
|
model-00006-of-00009.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de0e64803cd1551ed8339dcd9d831d663f0889875afc2357db4a006c7ae2f333
|
| 3 |
+
size 4939127704
|
model-00007-of-00009.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c039f20d8b07e407d778cf0005cbb8beac1e46fdb5fe5701b0fde1f784f54ee
|
| 3 |
+
size 4939127704
|
model-00008-of-00009.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98fce548fbfb2d09f2c9a91439b53f6e0b693cf94a35934714faf596bf6dca02
|
| 3 |
+
size 4939127704
|
model-00009-of-00009.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:67e3c5e2d98072f8d3a066842d22a822a5cae91fab5ee61e1d1ca89603e6e27f
|
| 3 |
+
size 2751362856
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,419 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 335424,
|
| 4 |
+
"total_size": 41829514368
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00009-of-00009.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00009.safetensors",
|
| 9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors",
|
| 10 |
+
"model.layers.0.mlp.experts.down_proj": "model-00001-of-00009.safetensors",
|
| 11 |
+
"model.layers.0.mlp.experts.down_proj_bias": "model-00001-of-00009.safetensors",
|
| 12 |
+
"model.layers.0.mlp.experts.gate_up_proj": "model-00001-of-00009.safetensors",
|
| 13 |
+
"model.layers.0.mlp.experts.gate_up_proj_bias": "model-00001-of-00009.safetensors",
|
| 14 |
+
"model.layers.0.mlp.router.bias": "model-00001-of-00009.safetensors",
|
| 15 |
+
"model.layers.0.mlp.router.weight": "model-00001-of-00009.safetensors",
|
| 16 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00009.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.o_proj.bias": "model-00001-of-00009.safetensors",
|
| 20 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
|
| 21 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00009.safetensors",
|
| 22 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
|
| 23 |
+
"model.layers.0.self_attn.sinks": "model-00001-of-00009.safetensors",
|
| 24 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00009.safetensors",
|
| 25 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
|
| 26 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors",
|
| 27 |
+
"model.layers.1.mlp.experts.down_proj": "model-00001-of-00009.safetensors",
|
| 28 |
+
"model.layers.1.mlp.experts.down_proj_bias": "model-00001-of-00009.safetensors",
|
| 29 |
+
"model.layers.1.mlp.experts.gate_up_proj": "model-00001-of-00009.safetensors",
|
| 30 |
+
"model.layers.1.mlp.experts.gate_up_proj_bias": "model-00001-of-00009.safetensors",
|
| 31 |
+
"model.layers.1.mlp.router.bias": "model-00001-of-00009.safetensors",
|
| 32 |
+
"model.layers.1.mlp.router.weight": "model-00001-of-00009.safetensors",
|
| 33 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
|
| 34 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00009.safetensors",
|
| 35 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
|
| 36 |
+
"model.layers.1.self_attn.o_proj.bias": "model-00001-of-00009.safetensors",
|
| 37 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
|
| 38 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00009.safetensors",
|
| 39 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
|
| 40 |
+
"model.layers.1.self_attn.sinks": "model-00001-of-00009.safetensors",
|
| 41 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00009.safetensors",
|
| 42 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
|
| 43 |
+
"model.layers.10.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
| 44 |
+
"model.layers.10.mlp.experts.down_proj": "model-00004-of-00009.safetensors",
|
| 45 |
+
"model.layers.10.mlp.experts.down_proj_bias": "model-00004-of-00009.safetensors",
|
| 46 |
+
"model.layers.10.mlp.experts.gate_up_proj": "model-00004-of-00009.safetensors",
|
| 47 |
+
"model.layers.10.mlp.experts.gate_up_proj_bias": "model-00004-of-00009.safetensors",
|
| 48 |
+
"model.layers.10.mlp.router.bias": "model-00004-of-00009.safetensors",
|
| 49 |
+
"model.layers.10.mlp.router.weight": "model-00004-of-00009.safetensors",
|
| 50 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
| 51 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
|
| 52 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
| 53 |
+
"model.layers.10.self_attn.o_proj.bias": "model-00004-of-00009.safetensors",
|
| 54 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
| 55 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
|
| 56 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
| 57 |
+
"model.layers.10.self_attn.sinks": "model-00004-of-00009.safetensors",
|
| 58 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
|
| 59 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
| 60 |
+
"model.layers.11.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
| 61 |
+
"model.layers.11.mlp.experts.down_proj": "model-00005-of-00009.safetensors",
|
| 62 |
+
"model.layers.11.mlp.experts.down_proj_bias": "model-00005-of-00009.safetensors",
|
| 63 |
+
"model.layers.11.mlp.experts.gate_up_proj": "model-00005-of-00009.safetensors",
|
| 64 |
+
"model.layers.11.mlp.experts.gate_up_proj_bias": "model-00005-of-00009.safetensors",
|
| 65 |
+
"model.layers.11.mlp.router.bias": "model-00004-of-00009.safetensors",
|
| 66 |
+
"model.layers.11.mlp.router.weight": "model-00004-of-00009.safetensors",
|
| 67 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
| 68 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
|
| 69 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
| 70 |
+
"model.layers.11.self_attn.o_proj.bias": "model-00004-of-00009.safetensors",
|
| 71 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
| 72 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
|
| 73 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
| 74 |
+
"model.layers.11.self_attn.sinks": "model-00004-of-00009.safetensors",
|
| 75 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
|
| 76 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
| 77 |
+
"model.layers.12.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
| 78 |
+
"model.layers.12.mlp.experts.down_proj": "model-00005-of-00009.safetensors",
|
| 79 |
+
"model.layers.12.mlp.experts.down_proj_bias": "model-00005-of-00009.safetensors",
|
| 80 |
+
"model.layers.12.mlp.experts.gate_up_proj": "model-00005-of-00009.safetensors",
|
| 81 |
+
"model.layers.12.mlp.experts.gate_up_proj_bias": "model-00005-of-00009.safetensors",
|
| 82 |
+
"model.layers.12.mlp.router.bias": "model-00005-of-00009.safetensors",
|
| 83 |
+
"model.layers.12.mlp.router.weight": "model-00005-of-00009.safetensors",
|
| 84 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
| 85 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
|
| 86 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
| 87 |
+
"model.layers.12.self_attn.o_proj.bias": "model-00005-of-00009.safetensors",
|
| 88 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
| 89 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
|
| 90 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
| 91 |
+
"model.layers.12.self_attn.sinks": "model-00005-of-00009.safetensors",
|
| 92 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
|
| 93 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
| 94 |
+
"model.layers.13.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
| 95 |
+
"model.layers.13.mlp.experts.down_proj": "model-00005-of-00009.safetensors",
|
| 96 |
+
"model.layers.13.mlp.experts.down_proj_bias": "model-00005-of-00009.safetensors",
|
| 97 |
+
"model.layers.13.mlp.experts.gate_up_proj": "model-00005-of-00009.safetensors",
|
| 98 |
+
"model.layers.13.mlp.experts.gate_up_proj_bias": "model-00005-of-00009.safetensors",
|
| 99 |
+
"model.layers.13.mlp.router.bias": "model-00005-of-00009.safetensors",
|
| 100 |
+
"model.layers.13.mlp.router.weight": "model-00005-of-00009.safetensors",
|
| 101 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
| 102 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
|
| 103 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
| 104 |
+
"model.layers.13.self_attn.o_proj.bias": "model-00005-of-00009.safetensors",
|
| 105 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
| 106 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
|
| 107 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
| 108 |
+
"model.layers.13.self_attn.sinks": "model-00005-of-00009.safetensors",
|
| 109 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
|
| 110 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
| 111 |
+
"model.layers.14.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
| 112 |
+
"model.layers.14.mlp.experts.down_proj": "model-00006-of-00009.safetensors",
|
| 113 |
+
"model.layers.14.mlp.experts.down_proj_bias": "model-00006-of-00009.safetensors",
|
| 114 |
+
"model.layers.14.mlp.experts.gate_up_proj": "model-00006-of-00009.safetensors",
|
| 115 |
+
"model.layers.14.mlp.experts.gate_up_proj_bias": "model-00006-of-00009.safetensors",
|
| 116 |
+
"model.layers.14.mlp.router.bias": "model-00005-of-00009.safetensors",
|
| 117 |
+
"model.layers.14.mlp.router.weight": "model-00005-of-00009.safetensors",
|
| 118 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
| 119 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
|
| 120 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
| 121 |
+
"model.layers.14.self_attn.o_proj.bias": "model-00005-of-00009.safetensors",
|
| 122 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
| 123 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
|
| 124 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
| 125 |
+
"model.layers.14.self_attn.sinks": "model-00005-of-00009.safetensors",
|
| 126 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
|
| 127 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
| 128 |
+
"model.layers.15.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
| 129 |
+
"model.layers.15.mlp.experts.down_proj": "model-00006-of-00009.safetensors",
|
| 130 |
+
"model.layers.15.mlp.experts.down_proj_bias": "model-00006-of-00009.safetensors",
|
| 131 |
+
"model.layers.15.mlp.experts.gate_up_proj": "model-00006-of-00009.safetensors",
|
| 132 |
+
"model.layers.15.mlp.experts.gate_up_proj_bias": "model-00006-of-00009.safetensors",
|
| 133 |
+
"model.layers.15.mlp.router.bias": "model-00006-of-00009.safetensors",
|
| 134 |
+
"model.layers.15.mlp.router.weight": "model-00006-of-00009.safetensors",
|
| 135 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
| 136 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
|
| 137 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
| 138 |
+
"model.layers.15.self_attn.o_proj.bias": "model-00006-of-00009.safetensors",
|
| 139 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
| 140 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
|
| 141 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
| 142 |
+
"model.layers.15.self_attn.sinks": "model-00006-of-00009.safetensors",
|
| 143 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
|
| 144 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
| 145 |
+
"model.layers.16.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
| 146 |
+
"model.layers.16.mlp.experts.down_proj": "model-00006-of-00009.safetensors",
|
| 147 |
+
"model.layers.16.mlp.experts.down_proj_bias": "model-00006-of-00009.safetensors",
|
| 148 |
+
"model.layers.16.mlp.experts.gate_up_proj": "model-00006-of-00009.safetensors",
|
| 149 |
+
"model.layers.16.mlp.experts.gate_up_proj_bias": "model-00006-of-00009.safetensors",
|
| 150 |
+
"model.layers.16.mlp.router.bias": "model-00006-of-00009.safetensors",
|
| 151 |
+
"model.layers.16.mlp.router.weight": "model-00006-of-00009.safetensors",
|
| 152 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
| 153 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
|
| 154 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
| 155 |
+
"model.layers.16.self_attn.o_proj.bias": "model-00006-of-00009.safetensors",
|
| 156 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
| 157 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
|
| 158 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
| 159 |
+
"model.layers.16.self_attn.sinks": "model-00006-of-00009.safetensors",
|
| 160 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
|
| 161 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
| 162 |
+
"model.layers.17.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
| 163 |
+
"model.layers.17.mlp.experts.down_proj": "model-00007-of-00009.safetensors",
|
| 164 |
+
"model.layers.17.mlp.experts.down_proj_bias": "model-00007-of-00009.safetensors",
|
| 165 |
+
"model.layers.17.mlp.experts.gate_up_proj": "model-00007-of-00009.safetensors",
|
| 166 |
+
"model.layers.17.mlp.experts.gate_up_proj_bias": "model-00007-of-00009.safetensors",
|
| 167 |
+
"model.layers.17.mlp.router.bias": "model-00006-of-00009.safetensors",
|
| 168 |
+
"model.layers.17.mlp.router.weight": "model-00006-of-00009.safetensors",
|
| 169 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
| 170 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
|
| 171 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
| 172 |
+
"model.layers.17.self_attn.o_proj.bias": "model-00006-of-00009.safetensors",
|
| 173 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
| 174 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
|
| 175 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
| 176 |
+
"model.layers.17.self_attn.sinks": "model-00006-of-00009.safetensors",
|
| 177 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
|
| 178 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
| 179 |
+
"model.layers.18.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
| 180 |
+
"model.layers.18.mlp.experts.down_proj": "model-00007-of-00009.safetensors",
|
| 181 |
+
"model.layers.18.mlp.experts.down_proj_bias": "model-00007-of-00009.safetensors",
|
| 182 |
+
"model.layers.18.mlp.experts.gate_up_proj": "model-00007-of-00009.safetensors",
|
| 183 |
+
"model.layers.18.mlp.experts.gate_up_proj_bias": "model-00007-of-00009.safetensors",
|
| 184 |
+
"model.layers.18.mlp.router.bias": "model-00007-of-00009.safetensors",
|
| 185 |
+
"model.layers.18.mlp.router.weight": "model-00007-of-00009.safetensors",
|
| 186 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
| 187 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
|
| 188 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
| 189 |
+
"model.layers.18.self_attn.o_proj.bias": "model-00007-of-00009.safetensors",
|
| 190 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
| 191 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
|
| 192 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
| 193 |
+
"model.layers.18.self_attn.sinks": "model-00007-of-00009.safetensors",
|
| 194 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
|
| 195 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
| 196 |
+
"model.layers.19.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
| 197 |
+
"model.layers.19.mlp.experts.down_proj": "model-00007-of-00009.safetensors",
|
| 198 |
+
"model.layers.19.mlp.experts.down_proj_bias": "model-00007-of-00009.safetensors",
|
| 199 |
+
"model.layers.19.mlp.experts.gate_up_proj": "model-00007-of-00009.safetensors",
|
| 200 |
+
"model.layers.19.mlp.experts.gate_up_proj_bias": "model-00007-of-00009.safetensors",
|
| 201 |
+
"model.layers.19.mlp.router.bias": "model-00007-of-00009.safetensors",
|
| 202 |
+
"model.layers.19.mlp.router.weight": "model-00007-of-00009.safetensors",
|
| 203 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
| 204 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
|
| 205 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
| 206 |
+
"model.layers.19.self_attn.o_proj.bias": "model-00007-of-00009.safetensors",
|
| 207 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
| 208 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
|
| 209 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
| 210 |
+
"model.layers.19.self_attn.sinks": "model-00007-of-00009.safetensors",
|
| 211 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
|
| 212 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
| 213 |
+
"model.layers.2.input_layernorm.weight": "model-00002-of-00009.safetensors",
|
| 214 |
+
"model.layers.2.mlp.experts.down_proj": "model-00002-of-00009.safetensors",
|
| 215 |
+
"model.layers.2.mlp.experts.down_proj_bias": "model-00002-of-00009.safetensors",
|
| 216 |
+
"model.layers.2.mlp.experts.gate_up_proj": "model-00002-of-00009.safetensors",
|
| 217 |
+
"model.layers.2.mlp.experts.gate_up_proj_bias": "model-00002-of-00009.safetensors",
|
| 218 |
+
"model.layers.2.mlp.router.bias": "model-00001-of-00009.safetensors",
|
| 219 |
+
"model.layers.2.mlp.router.weight": "model-00001-of-00009.safetensors",
|
| 220 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
|
| 221 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00009.safetensors",
|
| 222 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
|
| 223 |
+
"model.layers.2.self_attn.o_proj.bias": "model-00001-of-00009.safetensors",
|
| 224 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
|
| 225 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00009.safetensors",
|
| 226 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
|
| 227 |
+
"model.layers.2.self_attn.sinks": "model-00001-of-00009.safetensors",
|
| 228 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00009.safetensors",
|
| 229 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
|
| 230 |
+
"model.layers.20.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
| 231 |
+
"model.layers.20.mlp.experts.down_proj": "model-00008-of-00009.safetensors",
|
| 232 |
+
"model.layers.20.mlp.experts.down_proj_bias": "model-00008-of-00009.safetensors",
|
| 233 |
+
"model.layers.20.mlp.experts.gate_up_proj": "model-00008-of-00009.safetensors",
|
| 234 |
+
"model.layers.20.mlp.experts.gate_up_proj_bias": "model-00008-of-00009.safetensors",
|
| 235 |
+
"model.layers.20.mlp.router.bias": "model-00007-of-00009.safetensors",
|
| 236 |
+
"model.layers.20.mlp.router.weight": "model-00007-of-00009.safetensors",
|
| 237 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
| 238 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
|
| 239 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
| 240 |
+
"model.layers.20.self_attn.o_proj.bias": "model-00007-of-00009.safetensors",
|
| 241 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
| 242 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
|
| 243 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
| 244 |
+
"model.layers.20.self_attn.sinks": "model-00007-of-00009.safetensors",
|
| 245 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
|
| 246 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
| 247 |
+
"model.layers.21.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
| 248 |
+
"model.layers.21.mlp.experts.down_proj": "model-00008-of-00009.safetensors",
|
| 249 |
+
"model.layers.21.mlp.experts.down_proj_bias": "model-00008-of-00009.safetensors",
|
| 250 |
+
"model.layers.21.mlp.experts.gate_up_proj": "model-00008-of-00009.safetensors",
|
| 251 |
+
"model.layers.21.mlp.experts.gate_up_proj_bias": "model-00008-of-00009.safetensors",
|
| 252 |
+
"model.layers.21.mlp.router.bias": "model-00008-of-00009.safetensors",
|
| 253 |
+
"model.layers.21.mlp.router.weight": "model-00008-of-00009.safetensors",
|
| 254 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
| 255 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00008-of-00009.safetensors",
|
| 256 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
| 257 |
+
"model.layers.21.self_attn.o_proj.bias": "model-00008-of-00009.safetensors",
|
| 258 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
| 259 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00008-of-00009.safetensors",
|
| 260 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
| 261 |
+
"model.layers.21.self_attn.sinks": "model-00008-of-00009.safetensors",
|
| 262 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00008-of-00009.safetensors",
|
| 263 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
| 264 |
+
"model.layers.22.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
| 265 |
+
"model.layers.22.mlp.experts.down_proj": "model-00008-of-00009.safetensors",
|
| 266 |
+
"model.layers.22.mlp.experts.down_proj_bias": "model-00008-of-00009.safetensors",
|
| 267 |
+
"model.layers.22.mlp.experts.gate_up_proj": "model-00008-of-00009.safetensors",
|
| 268 |
+
"model.layers.22.mlp.experts.gate_up_proj_bias": "model-00008-of-00009.safetensors",
|
| 269 |
+
"model.layers.22.mlp.router.bias": "model-00008-of-00009.safetensors",
|
| 270 |
+
"model.layers.22.mlp.router.weight": "model-00008-of-00009.safetensors",
|
| 271 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
| 272 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00008-of-00009.safetensors",
|
| 273 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
| 274 |
+
"model.layers.22.self_attn.o_proj.bias": "model-00008-of-00009.safetensors",
|
| 275 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
| 276 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00008-of-00009.safetensors",
|
| 277 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
| 278 |
+
"model.layers.22.self_attn.sinks": "model-00008-of-00009.safetensors",
|
| 279 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00008-of-00009.safetensors",
|
| 280 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
| 281 |
+
"model.layers.23.input_layernorm.weight": "model-00009-of-00009.safetensors",
|
| 282 |
+
"model.layers.23.mlp.experts.down_proj": "model-00009-of-00009.safetensors",
|
| 283 |
+
"model.layers.23.mlp.experts.down_proj_bias": "model-00009-of-00009.safetensors",
|
| 284 |
+
"model.layers.23.mlp.experts.gate_up_proj": "model-00009-of-00009.safetensors",
|
| 285 |
+
"model.layers.23.mlp.experts.gate_up_proj_bias": "model-00009-of-00009.safetensors",
|
| 286 |
+
"model.layers.23.mlp.router.bias": "model-00008-of-00009.safetensors",
|
| 287 |
+
"model.layers.23.mlp.router.weight": "model-00008-of-00009.safetensors",
|
| 288 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
|
| 289 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00008-of-00009.safetensors",
|
| 290 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
| 291 |
+
"model.layers.23.self_attn.o_proj.bias": "model-00008-of-00009.safetensors",
|
| 292 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
| 293 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00008-of-00009.safetensors",
|
| 294 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
| 295 |
+
"model.layers.23.self_attn.sinks": "model-00008-of-00009.safetensors",
|
| 296 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00008-of-00009.safetensors",
|
| 297 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
| 298 |
+
"model.layers.3.input_layernorm.weight": "model-00002-of-00009.safetensors",
|
| 299 |
+
"model.layers.3.mlp.experts.down_proj": "model-00002-of-00009.safetensors",
|
| 300 |
+
"model.layers.3.mlp.experts.down_proj_bias": "model-00002-of-00009.safetensors",
|
| 301 |
+
"model.layers.3.mlp.experts.gate_up_proj": "model-00002-of-00009.safetensors",
|
| 302 |
+
"model.layers.3.mlp.experts.gate_up_proj_bias": "model-00002-of-00009.safetensors",
|
| 303 |
+
"model.layers.3.mlp.router.bias": "model-00002-of-00009.safetensors",
|
| 304 |
+
"model.layers.3.mlp.router.weight": "model-00002-of-00009.safetensors",
|
| 305 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
|
| 306 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00002-of-00009.safetensors",
|
| 307 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
|
| 308 |
+
"model.layers.3.self_attn.o_proj.bias": "model-00002-of-00009.safetensors",
|
| 309 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
|
| 310 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00002-of-00009.safetensors",
|
| 311 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
|
| 312 |
+
"model.layers.3.self_attn.sinks": "model-00002-of-00009.safetensors",
|
| 313 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00002-of-00009.safetensors",
|
| 314 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
|
| 315 |
+
"model.layers.4.input_layernorm.weight": "model-00002-of-00009.safetensors",
|
| 316 |
+
"model.layers.4.mlp.experts.down_proj": "model-00002-of-00009.safetensors",
|
| 317 |
+
"model.layers.4.mlp.experts.down_proj_bias": "model-00002-of-00009.safetensors",
|
| 318 |
+
"model.layers.4.mlp.experts.gate_up_proj": "model-00002-of-00009.safetensors",
|
| 319 |
+
"model.layers.4.mlp.experts.gate_up_proj_bias": "model-00002-of-00009.safetensors",
|
| 320 |
+
"model.layers.4.mlp.router.bias": "model-00002-of-00009.safetensors",
|
| 321 |
+
"model.layers.4.mlp.router.weight": "model-00002-of-00009.safetensors",
|
| 322 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
|
| 323 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00002-of-00009.safetensors",
|
| 324 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
|
| 325 |
+
"model.layers.4.self_attn.o_proj.bias": "model-00002-of-00009.safetensors",
|
| 326 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
|
| 327 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00002-of-00009.safetensors",
|
| 328 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
|
| 329 |
+
"model.layers.4.self_attn.sinks": "model-00002-of-00009.safetensors",
|
| 330 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00002-of-00009.safetensors",
|
| 331 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
|
| 332 |
+
"model.layers.5.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
| 333 |
+
"model.layers.5.mlp.experts.down_proj": "model-00003-of-00009.safetensors",
|
| 334 |
+
"model.layers.5.mlp.experts.down_proj_bias": "model-00003-of-00009.safetensors",
|
| 335 |
+
"model.layers.5.mlp.experts.gate_up_proj": "model-00003-of-00009.safetensors",
|
| 336 |
+
"model.layers.5.mlp.experts.gate_up_proj_bias": "model-00003-of-00009.safetensors",
|
| 337 |
+
"model.layers.5.mlp.router.bias": "model-00002-of-00009.safetensors",
|
| 338 |
+
"model.layers.5.mlp.router.weight": "model-00002-of-00009.safetensors",
|
| 339 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
| 340 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00002-of-00009.safetensors",
|
| 341 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
|
| 342 |
+
"model.layers.5.self_attn.o_proj.bias": "model-00002-of-00009.safetensors",
|
| 343 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
|
| 344 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00002-of-00009.safetensors",
|
| 345 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
|
| 346 |
+
"model.layers.5.self_attn.sinks": "model-00002-of-00009.safetensors",
|
| 347 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00002-of-00009.safetensors",
|
| 348 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
|
| 349 |
+
"model.layers.6.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
| 350 |
+
"model.layers.6.mlp.experts.down_proj": "model-00003-of-00009.safetensors",
|
| 351 |
+
"model.layers.6.mlp.experts.down_proj_bias": "model-00003-of-00009.safetensors",
|
| 352 |
+
"model.layers.6.mlp.experts.gate_up_proj": "model-00003-of-00009.safetensors",
|
| 353 |
+
"model.layers.6.mlp.experts.gate_up_proj_bias": "model-00003-of-00009.safetensors",
|
| 354 |
+
"model.layers.6.mlp.router.bias": "model-00003-of-00009.safetensors",
|
| 355 |
+
"model.layers.6.mlp.router.weight": "model-00003-of-00009.safetensors",
|
| 356 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
| 357 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
|
| 358 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
| 359 |
+
"model.layers.6.self_attn.o_proj.bias": "model-00003-of-00009.safetensors",
|
| 360 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
| 361 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
|
| 362 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
| 363 |
+
"model.layers.6.self_attn.sinks": "model-00003-of-00009.safetensors",
|
| 364 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
|
| 365 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
| 366 |
+
"model.layers.7.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
| 367 |
+
"model.layers.7.mlp.experts.down_proj": "model-00003-of-00009.safetensors",
|
| 368 |
+
"model.layers.7.mlp.experts.down_proj_bias": "model-00003-of-00009.safetensors",
|
| 369 |
+
"model.layers.7.mlp.experts.gate_up_proj": "model-00003-of-00009.safetensors",
|
| 370 |
+
"model.layers.7.mlp.experts.gate_up_proj_bias": "model-00003-of-00009.safetensors",
|
| 371 |
+
"model.layers.7.mlp.router.bias": "model-00003-of-00009.safetensors",
|
| 372 |
+
"model.layers.7.mlp.router.weight": "model-00003-of-00009.safetensors",
|
| 373 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
| 374 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
|
| 375 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
| 376 |
+
"model.layers.7.self_attn.o_proj.bias": "model-00003-of-00009.safetensors",
|
| 377 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
| 378 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
|
| 379 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
| 380 |
+
"model.layers.7.self_attn.sinks": "model-00003-of-00009.safetensors",
|
| 381 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
|
| 382 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
| 383 |
+
"model.layers.8.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
| 384 |
+
"model.layers.8.mlp.experts.down_proj": "model-00004-of-00009.safetensors",
|
| 385 |
+
"model.layers.8.mlp.experts.down_proj_bias": "model-00004-of-00009.safetensors",
|
| 386 |
+
"model.layers.8.mlp.experts.gate_up_proj": "model-00004-of-00009.safetensors",
|
| 387 |
+
"model.layers.8.mlp.experts.gate_up_proj_bias": "model-00004-of-00009.safetensors",
|
| 388 |
+
"model.layers.8.mlp.router.bias": "model-00003-of-00009.safetensors",
|
| 389 |
+
"model.layers.8.mlp.router.weight": "model-00003-of-00009.safetensors",
|
| 390 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
| 391 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
|
| 392 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
| 393 |
+
"model.layers.8.self_attn.o_proj.bias": "model-00003-of-00009.safetensors",
|
| 394 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
| 395 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
|
| 396 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
| 397 |
+
"model.layers.8.self_attn.sinks": "model-00003-of-00009.safetensors",
|
| 398 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
|
| 399 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
| 400 |
+
"model.layers.9.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
| 401 |
+
"model.layers.9.mlp.experts.down_proj": "model-00004-of-00009.safetensors",
|
| 402 |
+
"model.layers.9.mlp.experts.down_proj_bias": "model-00004-of-00009.safetensors",
|
| 403 |
+
"model.layers.9.mlp.experts.gate_up_proj": "model-00004-of-00009.safetensors",
|
| 404 |
+
"model.layers.9.mlp.experts.gate_up_proj_bias": "model-00004-of-00009.safetensors",
|
| 405 |
+
"model.layers.9.mlp.router.bias": "model-00004-of-00009.safetensors",
|
| 406 |
+
"model.layers.9.mlp.router.weight": "model-00004-of-00009.safetensors",
|
| 407 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
| 408 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
|
| 409 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
| 410 |
+
"model.layers.9.self_attn.o_proj.bias": "model-00004-of-00009.safetensors",
|
| 411 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
| 412 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
|
| 413 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
| 414 |
+
"model.layers.9.self_attn.sinks": "model-00004-of-00009.safetensors",
|
| 415 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
|
| 416 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
| 417 |
+
"model.norm.weight": "model-00009-of-00009.safetensors"
|
| 418 |
+
}
|
| 419 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|startoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|return|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0614fe83cadab421296e664e1f48f4261fa8fef6e03e63bb75c20f38e37d07d3
|
| 3 |
+
size 27868174
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,183 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"199998": {
|
| 4 |
+
"content": "<|startoftext|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"199999": {
|
| 12 |
+
"content": "<|endoftext|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"200000": {
|
| 20 |
+
"content": "<|reserved_200000|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"200001": {
|
| 28 |
+
"content": "<|reserved_200001|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"200002": {
|
| 36 |
+
"content": "<|return|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"200003": {
|
| 44 |
+
"content": "<|constrain|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"200004": {
|
| 52 |
+
"content": "<|reserved_200004|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"200005": {
|
| 60 |
+
"content": "<|channel|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"200006": {
|
| 68 |
+
"content": "<|start|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"200007": {
|
| 76 |
+
"content": "<|end|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"200008": {
|
| 84 |
+
"content": "<|message|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"200009": {
|
| 92 |
+
"content": "<|reserved_200009|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"200010": {
|
| 100 |
+
"content": "<|reserved_200010|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"200011": {
|
| 108 |
+
"content": "<|reserved_200011|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"200012": {
|
| 116 |
+
"content": "<|call|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"200013": {
|
| 124 |
+
"content": "<|reserved_200013|>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"200014": {
|
| 132 |
+
"content": "<|reserved_200014|>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"200015": {
|
| 140 |
+
"content": "<|reserved_200015|>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"200016": {
|
| 148 |
+
"content": "<|reserved_200016|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"200017": {
|
| 156 |
+
"content": "<|reserved_200017|>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"200018": {
|
| 164 |
+
"content": "<|endofprompt|>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
}
|
| 171 |
+
},
|
| 172 |
+
"bos_token": "<|startoftext|>",
|
| 173 |
+
"clean_up_tokenization_spaces": false,
|
| 174 |
+
"eos_token": "<|return|>",
|
| 175 |
+
"extra_special_tokens": {},
|
| 176 |
+
"model_input_names": [
|
| 177 |
+
"input_ids",
|
| 178 |
+
"attention_mask"
|
| 179 |
+
],
|
| 180 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 181 |
+
"pad_token": "<|endoftext|>",
|
| 182 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 183 |
+
}
|